WorldWideScience

Sample records for multiagent reinforcement learning

  1. Accelerating Multiagent Reinforcement Learning by Equilibrium Transfer.

    Science.gov (United States)

    Hu, Yujing; Gao, Yang; An, Bo

    2015-07-01

    An important approach in multiagent reinforcement learning (MARL) is equilibrium-based MARL, which adopts equilibrium solution concepts in game theory and requires agents to play equilibrium strategies at each state. However, most existing equilibrium-based MARL algorithms cannot scale due to a large number of computationally expensive equilibrium computations (e.g., computing Nash equilibria is PPAD-hard) during learning. For the first time, this paper finds that during the learning process of equilibrium-based MARL, the one-shot games corresponding to each state's successive visits often have the same or similar equilibria (for some states more than 90% of games corresponding to successive visits have similar equilibria). Inspired by this observation, this paper proposes to use equilibrium transfer to accelerate equilibrium-based MARL. The key idea of equilibrium transfer is to reuse previously computed equilibria when each agent has a small incentive to deviate. By introducing transfer loss and transfer condition, a novel framework called equilibrium transfer-based MARL is proposed. We prove that although equilibrium transfer brings transfer loss, equilibrium-based MARL algorithms can still converge to an equilibrium policy under certain assumptions. Experimental results in widely used benchmarks (e.g., grid world game, soccer game, and wall game) show that the proposed framework: 1) not only significantly accelerates equilibrium-based MARL (up to 96.7% reduction in learning time), but also achieves higher average rewards than algorithms without equilibrium transfer and 2) scales significantly better than algorithms without equilibrium transfer when the state/action space grows and the number of agents increases.

  2. Traffic light control by multiagent reinforcement learning systems

    NARCIS (Netherlands)

    Bakker, B.; Whiteson, S.; Kester, L.; Groen, F.C.A.; Babuška, R.; Groen, F.C.A.

    2010-01-01

    Traffic light control is one of the main means of controlling road traffic. Improving traffic control is important because it can lead to higher traffic throughput and reduced traffic congestion. This chapter describes multiagent reinforcement learning techniques for automatic optimization of

  3. Traffic Light Control by Multiagent Reinforcement Learning Systems

    NARCIS (Netherlands)

    Bakker, B.; Whiteson, S.; Kester, L.J.H.M.; Groen, F.C.A.

    2010-01-01

    Traffic light control is one of the main means of controlling road traffic. Improving traffic control is important because it can lead to higher traffic throughput and reduced traffic congestion. This chapter describes multiagent reinforcement learning techniques for automatic optimization of

  4. Multiagent cooperation and competition with deep reinforcement learning.

    Directory of Open Access Journals (Sweden)

    Ardi Tampuu

    Full Text Available Evolution of cooperation and competition can appear when multiple adaptive agents share a biological, social, or technological niche. In the present work we study how cooperation and competition emerge between autonomous agents that learn by reinforcement while using only their raw visual input as the state representation. In particular, we extend the Deep Q-Learning framework to multiagent environments to investigate the interaction between two learning agents in the well-known video game Pong. By manipulating the classical rewarding scheme of Pong we show how competitive and collaborative behaviors emerge. We also describe the progression from competitive to collaborative behavior when the incentive to cooperate is increased. Finally we show how learning by playing against another adaptive agent, instead of against a hard-wired algorithm, results in more robust strategies. The present work shows that Deep Q-Networks can become a useful tool for studying decentralized learning of multiagent systems coping with high-dimensional environments.

  5. Multiagent cooperation and competition with deep reinforcement learning.

    Science.gov (United States)

    Tampuu, Ardi; Matiisen, Tambet; Kodelja, Dorian; Kuzovkin, Ilya; Korjus, Kristjan; Aru, Juhan; Aru, Jaan; Vicente, Raul

    2017-01-01

    Evolution of cooperation and competition can appear when multiple adaptive agents share a biological, social, or technological niche. In the present work we study how cooperation and competition emerge between autonomous agents that learn by reinforcement while using only their raw visual input as the state representation. In particular, we extend the Deep Q-Learning framework to multiagent environments to investigate the interaction between two learning agents in the well-known video game Pong. By manipulating the classical rewarding scheme of Pong we show how competitive and collaborative behaviors emerge. We also describe the progression from competitive to collaborative behavior when the incentive to cooperate is increased. Finally we show how learning by playing against another adaptive agent, instead of against a hard-wired algorithm, results in more robust strategies. The present work shows that Deep Q-Networks can become a useful tool for studying decentralized learning of multiagent systems coping with high-dimensional environments.

  6. Multiagent cooperation and competition with deep reinforcement learning

    Science.gov (United States)

    Kodelja, Dorian; Kuzovkin, Ilya; Korjus, Kristjan; Aru, Juhan; Aru, Jaan; Vicente, Raul

    2017-01-01

    Evolution of cooperation and competition can appear when multiple adaptive agents share a biological, social, or technological niche. In the present work we study how cooperation and competition emerge between autonomous agents that learn by reinforcement while using only their raw visual input as the state representation. In particular, we extend the Deep Q-Learning framework to multiagent environments to investigate the interaction between two learning agents in the well-known video game Pong. By manipulating the classical rewarding scheme of Pong we show how competitive and collaborative behaviors emerge. We also describe the progression from competitive to collaborative behavior when the incentive to cooperate is increased. Finally we show how learning by playing against another adaptive agent, instead of against a hard-wired algorithm, results in more robust strategies. The present work shows that Deep Q-Networks can become a useful tool for studying decentralized learning of multiagent systems coping with high-dimensional environments. PMID:28380078

  7. Multiagent Reinforcement Learning with Regret Matching for Robot Soccer

    Directory of Open Access Journals (Sweden)

    Qiang Liu

    2013-01-01

    Full Text Available This paper proposes a novel multiagent reinforcement learning (MARL algorithm Nash- learning with regret matching, in which regret matching is used to speed up the well-known MARL algorithm Nash- learning. It is critical that choosing a suitable strategy for action selection to harmonize the relation between exploration and exploitation to enhance the ability of online learning for Nash- learning. In Markov Game the joint action of agents adopting regret matching algorithm can converge to a group of points of no-regret that can be viewed as coarse correlated equilibrium which includes Nash equilibrium in essence. It is can be inferred that regret matching can guide exploration of the state-action space so that the rate of convergence of Nash- learning algorithm can be increased. Simulation results on robot soccer validate that compared to original Nash- learning algorithm, the use of regret matching during the learning phase of Nash- learning has excellent ability of online learning and results in significant performance in terms of scores, average reward and policy convergence.

  8. Optimal control in microgrid using multi-agent reinforcement learning.

    Science.gov (United States)

    Li, Fu-Dong; Wu, Min; He, Yong; Chen, Xin

    2012-11-01

    This paper presents an improved reinforcement learning method to minimize electricity costs on the premise of satisfying the power balance and generation limit of units in a microgrid with grid-connected mode. Firstly, the microgrid control requirements are analyzed and the objective function of optimal control for microgrid is proposed. Then, a state variable "Average Electricity Price Trend" which is used to express the most possible transitions of the system is developed so as to reduce the complexity and randomicity of the microgrid, and a multi-agent architecture including agents, state variables, action variables and reward function is formulated. Furthermore, dynamic hierarchical reinforcement learning, based on change rate of key state variable, is established to carry out optimal policy exploration. The analysis shows that the proposed method is beneficial to handle the problem of "curse of dimensionality" and speed up learning in the unknown large-scale world. Finally, the simulation results under JADE (Java Agent Development Framework) demonstrate the validity of the presented method in optimal control for a microgrid with grid-connected mode. Copyright © 2012 ISA. Published by Elsevier Ltd. All rights reserved.

  9. An Analysis of Stochastic Game Theory for Multiagent Reinforcement Learning

    National Research Council Canada - National Science Library

    Bowling, Michael

    2000-01-01

    .... In this paper we contribute a comprehensive presentation of the relevant techniques for solving stochastic games from both the game theory community and reinforcement learning communities. We examine the assumptions and limitations of these algorithms, and identify similarities between these algorithms, single agent reinforcement learners, and basic game theory techniques.

  10. IMPLEMENTATION OF MULTIAGENT REINFORCEMENT LEARNING MECHANISM FOR OPTIMAL ISLANDING OPERATION OF DISTRIBUTION NETWORK

    DEFF Research Database (Denmark)

    Saleem, Arshad; Lind, Morten

    2008-01-01

    among electric power utilities to utilize modern information and communication technologies (ICT) in order to improve the automation of the distribution system. In this paper we present our work for the implementation of a dynamic multi-agent based distributed reinforcement learning mechanism...

  11. Multi-agent machine learning a reinforcement approach

    CERN Document Server

    Schwartz, H M

    2014-01-01

    The book begins with a chapter on traditional methods of supervised learning, covering recursive least squares learning, mean square error methods, and stochastic approximation. Chapter 2 covers single agent reinforcement learning. Topics include learning value functions, Markov games, and TD learning with eligibility traces. Chapter 3 discusses two player games including two player matrix games with both pure and mixed strategies. Numerous algorithms and examples are presented. Chapter 4 covers learning in multi-player games, stochastic games, and Markov games, focusing on learning multi-pla

  12. Multiagent Reinforcement Learning Dynamic Spectrum Access in Cognitive Radios

    Directory of Open Access Journals (Sweden)

    Wu Chun

    2014-02-01

    Full Text Available A multiuser independent Q-learning method which does not need information interaction is proposed for multiuser dynamic spectrum accessing in cognitive radios. The method adopts self-learning paradigm, in which each CR user performs reinforcement learning only through observing individual performance reward without spending communication resource on information interaction with others. The reward is defined suitably to present channel quality and channel conflict status. The learning strategy of sufficient exploration, preference for good channel, and punishment for channel conflict is designed to implement multiuser dynamic spectrum accessing. In two users two channels scenario, a fast learning algorithm is proposed and the convergence to maximal whole reward is proved. The simulation results show that, with the proposed method, the CR system can obtain convergence of Nash equilibrium with large probability and achieve great performance of whole reward.

  13. Adaptive Load Balancing of Parallel Applications with Multi-Agent Reinforcement Learning on Heterogeneous Systems

    Directory of Open Access Journals (Sweden)

    Johan Parent

    2004-01-01

    Full Text Available We report on the improvements that can be achieved by applying machine learning techniques, in particular reinforcement learning, for the dynamic load balancing of parallel applications. The applications being considered in this paper are coarse grain data intensive applications. Such applications put high pressure on the interconnect of the hardware. Synchronization and load balancing in complex, heterogeneous networks need fast, flexible, adaptive load balancing algorithms. Viewing a parallel application as a one-state coordination game in the framework of multi-agent reinforcement learning, and by using a recently introduced multi-agent exploration technique, we are able to improve upon the classic job farming approach. The improvements are achieved with limited computation and communication overhead.

  14. The Study of Reinforcement Learning for Traffic Self-Adaptive Control under Multiagent Markov Game Environment

    Directory of Open Access Journals (Sweden)

    Lun-Hui Xu

    2013-01-01

    Full Text Available Urban traffic self-adaptive control problem is dynamic and uncertain, so the states of traffic environment are hard to be observed. Efficient agent which controls a single intersection can be discovered automatically via multiagent reinforcement learning. However, in the majority of the previous works on this approach, each agent needed perfect observed information when interacting with the environment and learned individually with less efficient coordination. This study casts traffic self-adaptive control as a multiagent Markov game problem. The design employs traffic signal control agent (TSCA for each signalized intersection that coordinates with neighboring TSCAs. A mathematical model for TSCAs’ interaction is built based on nonzero-sum markov game which has been applied to let TSCAs learn how to cooperate. A multiagent Markov game reinforcement learning approach is constructed on the basis of single-agent Q-learning. This method lets each TSCA learn to update its Q-values under the joint actions and imperfect information. The convergence of the proposed algorithm is analyzed theoretically. The simulation results show that the proposed method is convergent and effective in realistic traffic self-adaptive control setting.

  15. Multiagent reinforcement learning for urban traffic control using coordination graphs

    NARCIS (Netherlands)

    Kuyer, L.; Whiteson, S.; Bakker, B.; Vlassis, N.

    2008-01-01

    Since traffic jams are ubiquitous in the modern world, optimizing the behavior of traffic lights for efficient traffic flow is a critically important goal. Though most current traffic lights use simple heuristic protocols, more efficient controllers can be discovered automatically via multiagent

  16. Fast Conflict Resolution Based on Reinforcement Learning in Multi-agent System

    Institute of Scientific and Technical Information of China (English)

    PIAOSonghao; HONGBingrong; CHUHaitao

    2004-01-01

    In multi-agent system where each agen thas a different goal (even the team of agents has the same goal), agents must be able to resolve conflicts arising in the process of achieving their goal. Many researchers presented methods for conflict resolution, e.g., Reinforcement learning (RL), but the conventional RL requires a large computation cost because every agent must learn, at the same time the overlap of actions selected by each agent results in local conflict. Therefore in this paper, we propose a novel method to solve these problems. In order to deal with the conflict within the multi-agent system, the concept of potential field function based Action selection priority level (ASPL) is brought forward. In this method, all kinds of environment factor that may have influence on the priority are effectively computed with the potential field function. So the priority to access the local resource can be decided rapidly. By avoiding the complex coordination mechanism used in general multi-agent system, the conflict in multi-agent system is settled more efficiently. Our system consists of RL with ASPL module and generalized rules module. Using ASPL, RL module chooses a proper cooperative behavior, and generalized rule module can accelerate the learning process. By applying the proposed method to Robot Soccer, the learning process can be accelerated. The results of simulation and real experiments indicate the effectiveness of the method.

  17. Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving

    OpenAIRE

    Shalev-Shwartz, Shai; Shammah, Shaked; Shashua, Amnon

    2016-01-01

    Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured urban roadways. Since there are many possible scenarios, manually tackling all possible cases will likely yield a too simplistic policy. Moreover, one must balance between unexpected behavior of other drivers/pedestrians and at the same time not to be too de...

  18. Fuzzy OLAP association rules mining-based modular reinforcement learning approach for multiagent systems.

    Science.gov (United States)

    Kaya, Mehmet; Alhajj, Reda

    2005-04-01

    Multiagent systems and data mining have recently attracted considerable attention in the field of computing. Reinforcement learning is the most commonly used learning process for multiagent systems. However, it still has some drawbacks, including modeling other learning agents present in the domain as part of the state of the environment, and some states are experienced much less than others, or some state-action pairs are never visited during the learning phase. Further, before completing the learning process, an agent cannot exhibit a certain behavior in some states that may be experienced sufficiently. In this study, we propose a novel multiagent learning approach to handle these problems. Our approach is based on utilizing the mining process for modular cooperative learning systems. It incorporates fuzziness and online analytical processing (OLAP) based mining to effectively process the information reported by agents. First, we describe a fuzzy data cube OLAP architecture which facilitates effective storage and processing of the state information reported by agents. This way, the action of the other agent, not even in the visual environment. of the agent under consideration, can simply be predicted by extracting online association rules, a well-known data mining technique, from the constructed data cube. Second, we present a new action selection model, which is also based on association rules mining. Finally, we generalize not sufficiently experienced states, by mining multilevel association rules from the proposed fuzzy data cube. Experimental results obtained on two different versions of a well-known pursuit domain show the robustness and effectiveness of the proposed fuzzy OLAP mining based modular learning approach. Finally, we tested the scalability of the approach presented in this paper and compared it with our previous work on modular-fuzzy Q-learning and ordinary Q-learning.

  19. FMRQ-A Multiagent Reinforcement Learning Algorithm for Fully Cooperative Tasks.

    Science.gov (United States)

    Zhang, Zhen; Zhao, Dongbin; Gao, Junwei; Wang, Dongqing; Dai, Yujie

    2017-06-01

    In this paper, we propose a multiagent reinforcement learning algorithm dealing with fully cooperative tasks. The algorithm is called frequency of the maximum reward Q-learning (FMRQ). FMRQ aims to achieve one of the optimal Nash equilibria so as to optimize the performance index in multiagent systems. The frequency of obtaining the highest global immediate reward instead of immediate reward is used as the reinforcement signal. With FMRQ each agent does not need the observation of the other agents' actions and only shares its state and reward at each step. We validate FMRQ through case studies of repeated games: four cases of two-player two-action and one case of three-player two-action. It is demonstrated that FMRQ can converge to one of the optimal Nash equilibria in these cases. Moreover, comparison experiments on tasks with multiple states and finite steps are conducted. One is box-pushing and the other one is distributed sensor network problem. Experimental results show that the proposed algorithm outperforms others with higher performance.

  20. Off-Policy Reinforcement Learning for Synchronization in Multiagent Graphical Games.

    Science.gov (United States)

    Li, Jinna; Modares, Hamidreza; Chai, Tianyou; Lewis, Frank L; Xie, Lihua

    2017-10-01

    This paper develops an off-policy reinforcement learning (RL) algorithm to solve optimal synchronization of multiagent systems. This is accomplished by using the framework of graphical games. In contrast to traditional control protocols, which require complete knowledge of agent dynamics, the proposed off-policy RL algorithm is a model-free approach, in that it solves the optimal synchronization problem without knowing any knowledge of the agent dynamics. A prescribed control policy, called behavior policy, is applied to each agent to generate and collect data for learning. An off-policy Bellman equation is derived for each agent to learn the value function for the policy under evaluation, called target policy, and find an improved policy, simultaneously. Actor and critic neural networks along with least-square approach are employed to approximate target control policies and value functions using the data generated by applying prescribed behavior policies. Finally, an off-policy RL algorithm is presented that is implemented in real time and gives the approximate optimal control policy for each agent using only measured data. It is shown that the optimal distributed policies found by the proposed algorithm satisfy the global Nash equilibrium and synchronize all agents to the leader. Simulation results illustrate the effectiveness of the proposed method.

  1. Switching dynamics of multi-agent learning

    NARCIS (Netherlands)

    Vrancx, P.; Tuyls, K.P.; Westra, R.

    2008-01-01

    This paper presents the dynamics of multi-agent reinforcement learning in multiple state problems. We extend previous work that formally modelled the relation between reinforcement learning agents and replicator dynamics in stateless multi-agent games. More precisely, in this work we use a

  2. Best Response Bayesian Reinforcement Learning for Multiagent Systems with State Uncertainty

    NARCIS (Netherlands)

    Oliehoek, F.A.; Amato, C.

    2014-01-01

    It is often assumed that agents in multiagent systems with state uncertainty have full knowledge of the model of dy- namics and sensors, but in many cases this is not feasible. A more realistic assumption is that agents must learn about the environment and other agents while acting. Bayesian methods

  3. Multiagent-Based Simulation of Temporal-Spatial Characteristics of Activity-Travel Patterns Using Interactive Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Min Yang

    2014-01-01

    Full Text Available We propose a multiagent-based reinforcement learning algorithm, in which the interactions between travelers and the environment are considered to simulate temporal-spatial characteristics of activity-travel patterns in a city. Road congestion degree is added to the reinforcement learning algorithm as a medium that passes the influence of one traveler’s decision to others. Meanwhile, the agents used in the algorithm are initialized from typical activity patterns extracted from the travel survey diary data of Shangyu city in China. In the simulation, both macroscopic activity-travel characteristics such as traffic flow spatial-temporal distribution and microscopic characteristics such as activity-travel schedules of each agent are obtained. Comparing the simulation results with the survey data, we find that deviation of the peak-hour traffic flow is less than 5%, while the correlation of the simulated versus survey location choice distribution is over 0.9.

  4. Scale-free memory model for multiagent reinforcement learning. Mean field approximation and rock-paper-scissors dynamics

    Science.gov (United States)

    Lubashevsky, I.; Kanemoto, S.

    2010-07-01

    A continuous time model for multiagent systems governed by reinforcement learning with scale-free memory is developed. The agents are assumed to act independently of one another in optimizing their choice of possible actions via trial-and-error search. To gain awareness about the action value the agents accumulate in their memory the rewards obtained from taking a specific action at each moment of time. The contribution of the rewards in the past to the agent current perception of action value is described by an integral operator with a power-law kernel. Finally a fractional differential equation governing the system dynamics is obtained. The agents are considered to interact with one another implicitly via the reward of one agent depending on the choice of the other agents. The pairwise interaction model is adopted to describe this effect. As a specific example of systems with non-transitive interactions, a two agent and three agent systems of the rock-paper-scissors type are analyzed in detail, including the stability analysis and numerical simulation. Scale-free memory is demonstrated to cause complex dynamics of the systems at hand. In particular, it is shown that there can be simultaneously two modes of the system instability undergoing subcritical and supercritical bifurcation, with the latter one exhibiting anomalous oscillations with the amplitude and period growing with time. Besides, the instability onset via this supercritical mode may be regarded as “altruism self-organization”. For the three agent system the instability dynamics is found to be rather irregular and can be composed of alternate fragments of oscillations different in their properties.

  5. Strategic farsighted learning in competitive multi-agent games

    NARCIS (Netherlands)

    t Hoen, P.J.; Bohté, S.M.; Poutré, la J.A.; Brewka, G.; Coradeschi, S.; Perini, A.

    2006-01-01

    We describe a generalized Q-learning type algorithm for reinforcement learning in competitive multi-agent games. We make the observation that in a competitive setting with adaptive agents an agent's actions will (likely) result in changes in the opponents policies. In addition to accounting for the

  6. Construction of multi-agent mobile robots control system in the problem of persecution with using a modified reinforcement learning method based on neural networks

    Science.gov (United States)

    Patkin, M. L.; Rogachev, G. N.

    2018-02-01

    A method for constructing a multi-agent control system for mobile robots based on training with reinforcement using deep neural networks is considered. Synthesis of the management system is proposed to be carried out with reinforcement training and the modified Actor-Critic method, in which the Actor module is divided into Action Actor and Communication Actor in order to simultaneously manage mobile robots and communicate with partners. Communication is carried out by sending partners at each step a vector of real numbers that are added to the observation vector and affect the behaviour. Functions of Actors and Critic are approximated by deep neural networks. The Critics value function is trained by using the TD-error method and the Actor’s function by using DDPG. The Communication Actor’s neural network is trained through gradients received from partner agents. An environment in which a cooperative multi-agent interaction is present was developed, computer simulation of the application of this method in the control problem of two robots pursuing two goals was carried out.

  7. Reinforcement Learning Multi-Agent Modeling of Decision-Making Agents for the Study of Transboundary Surface Water Conflicts with Application to the Syr Darya River Basin

    Science.gov (United States)

    Riegels, N.; Siegfried, T.; Pereira Cardenal, S. J.; Jensen, R. A.; Bauer-Gottwein, P.

    2008-12-01

    In most economics--driven approaches to optimizing water use at the river basin scale, the system is modelled deterministically with the goal of maximizing overall benefits. However, actual operation and allocation decisions must be made under hydrologic and economic uncertainty. In addition, river basins often cross political boundaries, and different states may not be motivated to cooperate so as to maximize basin- scale benefits. Even within states, competing agents such as irrigation districts, municipal water agencies, and large industrial users may not have incentives to cooperate to realize efficiency gains identified in basin- level studies. More traditional simulation--optimization approaches assume pre-commitment by individual agents and stakeholders and unconditional compliance on each side. While this can help determine attainable gains and tradeoffs from efficient management, such hardwired policies do not account for dynamic feedback between agents themselves or between agents and their environments (e.g. due to climate change etc.). In reality however, we are dealing with an out-of-equilibrium multi-agent system, where there is neither global knowledge nor global control, but rather continuous strategic interaction between decision making agents. Based on the theory of stochastic games, we present a computational framework that allows for studying the dynamic feedback between decision--making agents themselves and an inherently uncertain environment in a spatially and temporally distributed manner. Agents with decision-making control over water allocation such as countries, irrigation districts, and municipalities are represented by reinforcement learning agents and coupled to a detailed hydrologic--economic model. This approach emphasizes learning by agents from their continuous interaction with other agents and the environment. It provides a convenient framework for the solution of the problem of dynamic decision-making in a mixed cooperative / non

  8. Decentralized Reinforcement Learning of robot behaviors

    NARCIS (Netherlands)

    Leottau, David L.; Ruiz-del-Solar, Javier; Babuska, R.

    2018-01-01

    A multi-agent methodology is proposed for Decentralized Reinforcement Learning (DRL) of individual behaviors in problems where multi-dimensional action spaces are involved. When using this methodology, sub-tasks are learned in parallel by individual agents working toward a common goal. In

  9. Integrating distributed Bayesian inference and reinforcement learning for sensor management

    NARCIS (Netherlands)

    Grappiolo, C.; Whiteson, S.; Pavlin, G.; Bakker, B.

    2009-01-01

    This paper introduces a sensor management approach that integrates distributed Bayesian inference (DBI) and reinforcement learning (RL). DBI is implemented using distributed perception networks (DPNs), a multiagent approach to performing efficient inference, while RL is used to automatically

  10. Reinforcement learning in supply chains.

    Science.gov (United States)

    Valluri, Annapurna; North, Michael J; Macal, Charles M

    2009-10-01

    Effective management of supply chains creates value and can strategically position companies. In practice, human beings have been found to be both surprisingly successful and disappointingly inept at managing supply chains. The related fields of cognitive psychology and artificial intelligence have postulated a variety of potential mechanisms to explain this behavior. One of the leading candidates is reinforcement learning. This paper applies agent-based modeling to investigate the comparative behavioral consequences of three simple reinforcement learning algorithms in a multi-stage supply chain. For the first time, our findings show that the specific algorithm that is employed can have dramatic effects on the results obtained. Reinforcement learning is found to be valuable in multi-stage supply chains with several learning agents, as independent agents can learn to coordinate their behavior. However, learning in multi-stage supply chains using these postulated approaches from cognitive psychology and artificial intelligence take extremely long time periods to achieve stability which raises questions about their ability to explain behavior in real supply chains. The fact that it takes thousands of periods for agents to learn in this simple multi-agent setting provides new evidence that real world decision makers are unlikely to be using strict reinforcement learning in practice.

  11. Multiagent -Learning for Aloha-Like Spectrum Access in Cognitive Radio Systems

    Directory of Open Access Journals (Sweden)

    Li Husheng

    2010-01-01

    Full Text Available An Aloha-like spectrum access scheme without negotiation is considered for multiuser and multichannel cognitive radio systems. To avoid collisions incurred by the lack of coordination, each secondary user learns how to select channels according to its experience. Multiagent reinforcement leaning (MARL is applied for the secondary users to learn good strategies of channel selection. Specifically, the framework of -learning is extended from single user case to multiagent case by considering other secondary users as a part of the environment. The dynamics of the -learning are illustrated using a Metrick-Polak plot, which shows the traces of -values in the two-user case. For both complete and partial observation cases, rigorous proofs of the convergence of multiagent -learning without communications, under certain conditions, are provided using the Robins-Monro algorithm and contraction mapping, respectively. The learning performance (speed and gain in utility is evaluated by numerical simulations.

  12. Coupled replicator equations for the dynamics of learning in multiagent systems

    Science.gov (United States)

    Sato, Yuzuru; Crutchfield, James P.

    2003-01-01

    Starting with a group of reinforcement-learning agents we derive coupled replicator equations that describe the dynamics of collective learning in multiagent systems. We show that, although agents model their environment in a self-interested way without sharing knowledge, a game dynamics emerges naturally through environment-mediated interactions. An application to rock-scissors-paper game interactions shows that the collective learning dynamics exhibits a diversity of competitive and cooperative behaviors. These include quasiperiodicity, stable limit cycles, intermittency, and deterministic chaos—behaviors that should be expected in heterogeneous multiagent systems described by the general replicator equations we derive.

  13. Algorithms for Reinforcement Learning

    CERN Document Server

    Szepesvari, Csaba

    2010-01-01

    Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. What distinguishes reinforcement learning from supervised learning is that only partial feedback is given to the learner about the learner's predictions. Further, the predictions may have long term effects through influencing the future state of the controlled system. Thus, time plays a special role. The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms'

  14. Multi-agents and learning: Implications for Webusage mining

    Science.gov (United States)

    Lotfy, Hewayda M.S.; Khamis, Soheir M.S.; Aboghazalah, Maie M.

    2015-01-01

    Characterization of user activities is an important issue in the design and maintenance of websites. Server weblog files have abundant information about the user’s current interests. This information can be mined and analyzed therefore the administrators may be able to guide the users in their browsing activity so they may obtain relevant information in a shorter span of time to obtain user satisfaction. Web-based technology facilitates the creation of personally meaningful and socially useful knowledge through supportive interactions, communication and collaboration among educators, learners and information. This paper suggests a new methodology based on learning techniques for a Web-based Multiagent-based application to discover the hidden patterns in the user’s visited links. It presents a new approach that involves unsupervised, reinforcement learning, and cooperation between agents. It is utilized to discover patterns that represent the user’s profiles in a sample website into specific categories of materials using significance percentages. These profiles are used to make recommendations of interesting links and categories to the user. The experimental results of the approach showed successful user pattern recognition, and cooperative learning among agents to obtain user profiles. It indicates that combining different learning algorithms is capable of improving user satisfaction indicated by the percentage of precision, recall, the progressive category weight and F1-measure. PMID:26966569

  15. Multi-Agent Framework for Virtual Learning Spaces.

    Science.gov (United States)

    Sheremetov, Leonid; Nunez, Gustavo

    1999-01-01

    Discussion of computer-supported collaborative learning, distributed artificial intelligence, and intelligent tutoring systems focuses on the concept of agents, and describes a virtual learning environment that has a multi-agent system. Describes a model of interactions in collaborative learning and discusses agents for Web-based virtual…

  16. Reinforcement Learning for a New Piano Mover

    Directory of Open Access Journals (Sweden)

    Yuko Ishiwaka

    2005-08-01

    Full Text Available We attempt to achieve corporative behavior of autonomous decentralized agents constructed via Q-Learning, which is a type of reinforcement learning. As such, in the present paper, we examine the piano mover's problem. We propose a multi-agent architecture that has a training agent, learning agents and intermediate agent. Learning agents are heterogeneous and can communicate with each other. The movement of an object with three kinds of agent depends on the composition of the actions of the learning agents. By learning its own shape through the learning agents, avoidance of obstacles by the object is expected. We simulate the proposed method in a two-dimensional continuous world. Results obtained in the present investigation reveal the effectiveness of the proposed method.

  17. Learning in engineered multi-agent systems

    Science.gov (United States)

    Menon, Anup

    Consider the problem of maximizing the total power produced by a wind farm. Due to aerodynamic interactions between wind turbines, each turbine maximizing its individual power---as is the case in present-day wind farms---does not lead to optimal farm-level power capture. Further, there are no good models to capture the said aerodynamic interactions, rendering model based optimization techniques ineffective. Thus, model-free distributed algorithms are needed that help turbines adapt their power production on-line so as to maximize farm-level power capture. Motivated by such problems, the main focus of this dissertation is a distributed model-free optimization problem in the context of multi-agent systems. The set-up comprises of a fixed number of agents, each of which can pick an action and observe the value of its individual utility function. An individual's utility function may depend on the collective action taken by all agents. The exact functional form (or model) of the agent utility functions, however, are unknown; an agent can only measure the numeric value of its utility. The objective of the multi-agent system is to optimize the welfare function (i.e. sum of the individual utility functions). Such a collaborative task requires communications between agents and we allow for the possibility of such inter-agent communications. We also pay attention to the role played by the pattern of such information exchange on certain aspects of performance. We develop two algorithms to solve this problem. The first one, engineered Interactive Trial and Error Learning (eITEL) algorithm, is based on a line of work in the Learning in Games literature and applies when agent actions are drawn from finite sets. While in a model-free setting, we introduce a novel qualitative graph-theoretic framework to encode known directed interactions of the form "which agents' action affect which others' payoff" (interaction graph). We encode explicit inter-agent communications in a directed

  18. Manifold Regularized Reinforcement Learning.

    Science.gov (United States)

    Li, Hongliang; Liu, Derong; Wang, Ding

    2018-04-01

    This paper introduces a novel manifold regularized reinforcement learning scheme for continuous Markov decision processes. Smooth feature representations for value function approximation can be automatically learned using the unsupervised manifold regularization method. The learned features are data-driven, and can be adapted to the geometry of the state space. Furthermore, the scheme provides a direct basis representation extension for novel samples during policy learning and control. The performance of the proposed scheme is evaluated on two benchmark control tasks, i.e., the inverted pendulum and the energy storage problem. Simulation results illustrate the concepts of the proposed scheme and show that it can obtain excellent performance.

  19. The Reinforcement Learning Competition 2014

    OpenAIRE

    Dimitrakakis, Christos; Li, Guangliang; Tziortziotis, Nikoalos

    2014-01-01

    Reinforcement learning is one of the most general problems in artificial intelligence. It has been used to model problems in automated experiment design, control, economics, game playing, scheduling and telecommunications. The aim of the reinforcement learning competition is to encourage the development of very general learning agents for arbitrary reinforcement learning problems and to provide a test-bed for the unbiased evaluation of algorithms.

  20. Effect of reinforcement learning on coordination of multiangent systems

    Science.gov (United States)

    Bukkapatnam, Satish T. S.; Gao, Greg

    2000-12-01

    For effective coordination of distributed environments involving multiagent systems, learning ability of each agent in the environment plays a crucial role. In this paper, we develop a simple group learning method based on reinforcement, and study its effect on coordination through application to a supply chain procurement scenario involving a computer manufacturer. Here, all parties are represented by self-interested, autonomous agents, each capable of performing specific simple tasks. They negotiate with each other to perform complex tasks and thus coordinate supply chain procurement. Reinforcement learning is intended to enable each agent to reach a best negotiable price within a shortest possible time. Our simulations of the application scenario under different learning strategies reveals the positive effects of reinforcement learning on an agent's as well as the system's performance.

  1. Agendas for Multi-Agent Learning

    National Research Council Canada - National Science Library

    Gordon, Geoffrey J

    2006-01-01

    .... We then consider research goals for modelling, design, and learning, and identify the problem of finding learning algorithms that guarantee convergence to Pareto-dominant equilibria against a wide range of opponents...

  2. Optimal and Autonomous Control Using Reinforcement Learning: A Survey.

    Science.gov (United States)

    Kiumarsi, Bahare; Vamvoudakis, Kyriakos G; Modares, Hamidreza; Lewis, Frank L

    2018-06-01

    This paper reviews the current state of the art on reinforcement learning (RL)-based feedback control solutions to optimal regulation and tracking of single and multiagent systems. Existing RL solutions to both optimal and control problems, as well as graphical games, will be reviewed. RL methods learn the solution to optimal control and game problems online and using measured data along the system trajectories. We discuss Q-learning and the integral RL algorithm as core algorithms for discrete-time (DT) and continuous-time (CT) systems, respectively. Moreover, we discuss a new direction of off-policy RL for both CT and DT systems. Finally, we review several applications.

  3. Deep Reinforcement Learning: An Overview

    OpenAIRE

    Li, Yuxi

    2017-01-01

    We give an overview of recent exciting achievements of deep reinforcement learning (RL). We discuss six core elements, six important mechanisms, and twelve applications. We start with background of machine learning, deep learning and reinforcement learning. Next we discuss core RL elements, including value function, in particular, Deep Q-Network (DQN), policy, reward, model, planning, and exploration. After that, we discuss important mechanisms for RL, including attention and memory, unsuperv...

  4. Sample efficient multiagent learning in the presence of Markovian agents

    CERN Document Server

    Chakraborty, Doran

    2014-01-01

    The problem of Multiagent Learning (or MAL) is concerned with the study of how intelligent entities can learn and adapt in the presence of other such entities that are simultaneously adapting. The problem is often studied in the stylized settings provided by repeated matrix games (a.k.a. normal form games). The goal of this book is to develop MAL algorithms for such a setting that achieve a new set of objectives which have not been previously achieved. In particular this book deals with learning in the presence of a new class of agent behavior that has not been studied or modeled before in a MAL context: Markovian agent behavior. Several new challenges arise when interacting with this particular class of agents. The book takes a series of steps towards building completely autonomous learning algorithms that maximize utility while interacting with such agents. Each algorithm is meticulously specified with a thorough formal treatment that elucidates its key theoretical properties.

  5. Behavior Self-Organization in Multi-Agent Learning

    National Research Council Canada - National Science Library

    Bay, John

    1999-01-01

    There are four primary results of the first year of the project: It was discovered that clustering algorithms for pre-sorting high-dimensional datasets was not effective in improving subsequent processing by reinforcement learning methods...

  6. Collective Machine Learning: Team Learning and Classification in Multi-Agent Systems

    Science.gov (United States)

    Gifford, Christopher M.

    2009-01-01

    This dissertation focuses on the collaboration of multiple heterogeneous, intelligent agents (hardware or software) which collaborate to learn a task and are capable of sharing knowledge. The concept of collaborative learning in multi-agent and multi-robot systems is largely under studied, and represents an area where further research is needed to…

  7. Evolutionary computation for reinforcement learning

    NARCIS (Netherlands)

    Whiteson, S.; Wiering, M.; van Otterlo, M.

    2012-01-01

    Algorithms for evolutionary computation, which simulate the process of natural selection to solve optimization problems, are an effective tool for discovering high-performing reinforcement-learning policies. Because they can automatically find good representations, handle continuous action spaces,

  8. Iterative learning control for multi-agent systems coordination

    CERN Document Server

    Yang, Shiping; Li, Xuefang; Shen, Dong

    2016-01-01

    A timely guide using iterative learning control (ILC) as a solution for multi-agent systems (MAS) challenges, this book showcases recent advances and industrially relevant applications. Readers are first given a comprehensive overview of the intersection between ILC and MAS, then introduced to a range of topics that include both basic and advanced theoretical discussions, rigorous mathematics, engineering practice, and both linear and nonlinear systems. Through systematic discussion of network theory and intelligent control, the authors explore future research possibilities, develop new tools, and provide numerous applications such as power grids, communication and sensor networks, intelligent transportation systems, and formation control. Readers will gain a roadmap of the latest advances in the fields and can use their newfound knowledge to design their own algorithms.

  9. Multiagent Cooperative Learning Strategies for Pursuit-Evasion Games

    Directory of Open Access Journals (Sweden)

    Jong Yih Kuo

    2015-01-01

    Full Text Available This study examines the pursuit-evasion problem for coordinating multiple robotic pursuers to locate and track a nonadversarial mobile evader in a dynamic environment. Two kinds of pursuit strategies are proposed, one for agents that cooperate with each other and the other for agents that operate independently. This work further employs the probabilistic theory to analyze the uncertain state information about the pursuers and the evaders and uses case-based reasoning to equip agents with memories and learning abilities. According to the concepts of assimilation and accommodation, both positive-angle and bevel-angle strategies are developed to assist agents in adapting to their environment effectively. The case study analysis uses the Recursive Porous Agent Simulation Toolkit (REPAST to implement a multiagent system and demonstrates superior performance of the proposed approaches to the pursuit-evasion game.

  10. "Notice of Violation of IEEE Publication Principles" Multiobjective Reinforcement Learning: A Comprehensive Overview.

    Science.gov (United States)

    Liu, Chunming; Xu, Xin; Hu, Dewen

    2013-04-29

    Reinforcement learning is a powerful mechanism for enabling agents to learn in an unknown environment, and most reinforcement learning algorithms aim to maximize some numerical value, which represents only one long-term objective. However, multiple long-term objectives are exhibited in many real-world decision and control problems; therefore, recently, there has been growing interest in solving multiobjective reinforcement learning (MORL) problems with multiple conflicting objectives. The aim of this paper is to present a comprehensive overview of MORL. In this paper, the basic architecture, research topics, and naive solutions of MORL are introduced at first. Then, several representative MORL approaches and some important directions of recent research are reviewed. The relationships between MORL and other related research are also discussed, which include multiobjective optimization, hierarchical reinforcement learning, and multi-agent reinforcement learning. Finally, research challenges and open problems of MORL techniques are highlighted.

  11. Adaptive representations for reinforcement learning

    NARCIS (Netherlands)

    Whiteson, S.

    2010-01-01

    This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own

  12. An Improved Reinforcement Learning System Using Affective Factors

    Directory of Open Access Journals (Sweden)

    Takashi Kuremoto

    2013-07-01

    Full Text Available As a powerful and intelligent machine learning method, reinforcement learning (RL has been widely used in many fields such as game theory, adaptive control, multi-agent system, nonlinear forecasting, and so on. The main contribution of this technique is its exploration and exploitation approaches to find the optimal solution or semi-optimal solution of goal-directed problems. However, when RL is applied to multi-agent systems (MASs, problems such as “curse of dimension”, “perceptual aliasing problem”, and uncertainty of the environment constitute high hurdles to RL. Meanwhile, although RL is inspired by behavioral psychology and reward/punishment from the environment is used, higher mental factors such as affects, emotions, and motivations are rarely adopted in the learning procedure of RL. In this paper, to challenge agents learning in MASs, we propose a computational motivation function, which adopts two principle affective factors “Arousal” and “Pleasure” of Russell’s circumplex model of affects, to improve the learning performance of a conventional RL algorithm named Q-learning (QL. Compared with the conventional QL, computer simulations of pursuit problems with static and dynamic preys were carried out, and the results showed that the proposed method results in agents having a faster and more stable learning performance.

  13. Reinforcement learning in computer vision

    Science.gov (United States)

    Bernstein, A. V.; Burnaev, E. V.

    2018-04-01

    Nowadays, machine learning has become one of the basic technologies used in solving various computer vision tasks such as feature detection, image segmentation, object recognition and tracking. In many applications, various complex systems such as robots are equipped with visual sensors from which they learn state of surrounding environment by solving corresponding computer vision tasks. Solutions of these tasks are used for making decisions about possible future actions. It is not surprising that when solving computer vision tasks we should take into account special aspects of their subsequent application in model-based predictive control. Reinforcement learning is one of modern machine learning technologies in which learning is carried out through interaction with the environment. In recent years, Reinforcement learning has been used both for solving such applied tasks as processing and analysis of visual information, and for solving specific computer vision problems such as filtering, extracting image features, localizing objects in scenes, and many others. The paper describes shortly the Reinforcement learning technology and its use for solving computer vision problems.

  14. Rational and Mechanistic Perspectives on Reinforcement Learning

    Science.gov (United States)

    Chater, Nick

    2009-01-01

    This special issue describes important recent developments in applying reinforcement learning models to capture neural and cognitive function. But reinforcement learning, as a theoretical framework, can apply at two very different levels of description: "mechanistic" and "rational." Reinforcement learning is often viewed in mechanistic terms--as…

  15. Dynamically analyzing cell interactions in biological environments using multiagent social learning framework.

    Science.gov (United States)

    Zhang, Chengwei; Li, Xiaohong; Li, Shuxin; Feng, Zhiyong

    2017-09-20

    Biological environment is uncertain and its dynamic is similar to the multiagent environment, thus the research results of the multiagent system area can provide valuable insights to the understanding of biology and are of great significance for the study of biology. Learning in a multiagent environment is highly dynamic since the environment is not stationary anymore and each agent's behavior changes adaptively in response to other coexisting learners, and vice versa. The dynamics becomes more unpredictable when we move from fixed-agent interaction environments to multiagent social learning framework. Analytical understanding of the underlying dynamics is important and challenging. In this work, we present a social learning framework with homogeneous learners (e.g., Policy Hill Climbing (PHC) learners), and model the behavior of players in the social learning framework as a hybrid dynamical system. By analyzing the dynamical system, we obtain some conditions about convergence or non-convergence. We experimentally verify the predictive power of our model using a number of representative games. Experimental results confirm the theoretical analysis. Under multiagent social learning framework, we modeled the behavior of agent in biologic environment, and theoretically analyzed the dynamics of the model. We present some sufficient conditions about convergence or non-convergence and prove them theoretically. It can be used to predict the convergence of the system.

  16. Model of Recommendation System for for Indexing and Retrieving the Learning Object based on Multiagent System

    Directory of Open Access Journals (Sweden)

    Ronaldo Lima Rocha Campos

    2012-07-01

    Full Text Available This paper proposes a multiagent system application model for indexing, retrieving and recommendation learning objects stored in different and heterogeneous repositories. The objects within these repositories are described by filled fields using different metadata standards. The searching mechanism covers several different learning object repositories and the same object can be described in these repositories by the use of different types of fields. Aiming to improve accuracy and coverage in terms of recovering a learning object and improve the signification of the results we propose an information retrieval model based on the multiagent system approach and an ontological model to describe the knowledge domain covered.

  17. Reinforcement learning agents providing advice in complex video games

    Science.gov (United States)

    Taylor, Matthew E.; Carboni, Nicholas; Fachantidis, Anestis; Vlahavas, Ioannis; Torrey, Lisa

    2014-01-01

    This article introduces a teacher-student framework for reinforcement learning, synthesising and extending material that appeared in conference proceedings [Torrey, L., & Taylor, M. E. (2013)]. Teaching on a budget: Agents advising agents in reinforcement learning. {Proceedings of the international conference on autonomous agents and multiagent systems}] and in a non-archival workshop paper [Carboni, N., &Taylor, M. E. (2013, May)]. Preliminary results for 1 vs. 1 tactics in StarCraft. {Proceedings of the adaptive and learning agents workshop (at AAMAS-13)}]. In this framework, a teacher agent instructs a student agent by suggesting actions the student should take as it learns. However, the teacher may only give such advice a limited number of times. We present several novel algorithms that teachers can use to budget their advice effectively, and we evaluate them in two complex video games: StarCraft and Pac-Man. Our results show that the same amount of advice, given at different moments, can have different effects on student learning, and that teachers can significantly affect student learning even when students use different learning methods and state representations.

  18. An overview of cooperative and competitive multiagent learning

    NARCIS (Netherlands)

    t Hoen, P.J.; Tuyls, K.P.; Panait, L.; Luke, S.; Poutré, la J.A.; Hoen, 't P.J.; Tuyls, K.

    2006-01-01

    Multi-agent systems (MASs) is an area of distributed artificial intelligence that emphasizes the joint behaviors of agents with some degree of autonomy and the complexities arising from their interactions. The research on MASs is intensifying, as supported by a growing number of conferences,

  19. Belief reward shaping in reinforcement learning

    CSIR Research Space (South Africa)

    Marom, O

    2018-02-01

    Full Text Available A key challenge in many reinforcement learning problems is delayed rewards, which can significantly slow down learning. Although reward shaping has previously been introduced to accelerate learning by bootstrapping an agent with additional...

  20. Personalised learning object based on multi-agent model and learners’ learning styles

    Directory of Open Access Journals (Sweden)

    Noppamas Pukkhem

    2011-09-01

    Full Text Available A multi-agent model is proposed in which learning styles and a word analysis technique to create a learning object recommendation system are used. On the basis of a learning style-based design, a concept map combination model is proposed to filter out unsuitable learning concepts from a given course. Our learner model classifies learners into eight styles and implements compatible computational methods consisting of three recommendations: i non-personalised, ii preferred feature-based, and iii neighbour-based collaborative filtering. The analysis of preference error (PE was performed by comparing the actual preferred learning object with the predicted one. In our experiments, the feature-based recommendation algorithm has the fewest PE.

  1. Reinforcement learning or active inference?

    Science.gov (United States)

    Friston, Karl J; Daunizeau, Jean; Kiebel, Stefan J

    2009-07-29

    This paper questions the need for reinforcement learning or control theory when optimising behaviour. We show that it is fairly simple to teach an agent complicated and adaptive behaviours using a free-energy formulation of perception. In this formulation, agents adjust their internal states and sampling of the environment to minimize their free-energy. Such agents learn causal structure in the environment and sample it in an adaptive and self-supervised fashion. This results in behavioural policies that reproduce those optimised by reinforcement learning and dynamic programming. Critically, we do not need to invoke the notion of reward, value or utility. We illustrate these points by solving a benchmark problem in dynamic programming; namely the mountain-car problem, using active perception or inference under the free-energy principle. The ensuing proof-of-concept may be important because the free-energy formulation furnishes a unified account of both action and perception and may speak to a reappraisal of the role of dopamine in the brain.

  2. Reinforcement learning or active inference?

    Directory of Open Access Journals (Sweden)

    Karl J Friston

    2009-07-01

    Full Text Available This paper questions the need for reinforcement learning or control theory when optimising behaviour. We show that it is fairly simple to teach an agent complicated and adaptive behaviours using a free-energy formulation of perception. In this formulation, agents adjust their internal states and sampling of the environment to minimize their free-energy. Such agents learn causal structure in the environment and sample it in an adaptive and self-supervised fashion. This results in behavioural policies that reproduce those optimised by reinforcement learning and dynamic programming. Critically, we do not need to invoke the notion of reward, value or utility. We illustrate these points by solving a benchmark problem in dynamic programming; namely the mountain-car problem, using active perception or inference under the free-energy principle. The ensuing proof-of-concept may be important because the free-energy formulation furnishes a unified account of both action and perception and may speak to a reappraisal of the role of dopamine in the brain.

  3. CLEANing the Reward: Counterfactual Actions to Remove Exploratory Action Noise in Multiagent Learning

    Science.gov (United States)

    HolmesParker, Chris; Taylor, Mathew E.; Tumer, Kagan; Agogino, Adrian

    2014-01-01

    Learning in multiagent systems can be slow because agents must learn both how to behave in a complex environment and how to account for the actions of other agents. The inability of an agent to distinguish between the true environmental dynamics and those caused by the stochastic exploratory actions of other agents creates noise in each agent's reward signal. This learning noise can have unforeseen and often undesirable effects on the resultant system performance. We define such noise as exploratory action noise, demonstrate the critical impact it can have on the learning process in multiagent settings, and introduce a reward structure to effectively remove such noise from each agent's reward signal. In particular, we introduce Coordinated Learning without Exploratory Action Noise (CLEAN) rewards and empirically demonstrate their benefits

  4. Reinforcement Learning State-of-the-Art

    CERN Document Server

    Wiering, Marco

    2012-01-01

    Reinforcement learning encompasses both a science of adaptive behavior of rational beings in uncertain environments and a computational methodology for finding optimal behaviors for challenging problems in control, optimization and adaptive behavior of intelligent agents. As a field, reinforcement learning has progressed tremendously in the past decade. The main goal of this book is to present an up-to-date series of survey articles on the main contemporary sub-fields of reinforcement learning. This includes surveys on partially observable environments, hierarchical task decompositions, relational knowledge representation and predictive state representations. Furthermore, topics such as transfer, evolutionary methods and continuous spaces in reinforcement learning are surveyed. In addition, several chapters review reinforcement learning methods in robotics, in games, and in computational neuroscience. In total seventeen different subfields are presented by mostly young experts in those areas, and together the...

  5. Reinforcement Learning in Repeated Portfolio Decisions

    OpenAIRE

    Diao, Linan; Rieskamp, Jörg

    2011-01-01

    How do people make investment decisions when they receive outcome feedback? We examined how well the standard mean-variance model and two reinforcement models predict people's portfolio decisions. The basic reinforcement model predicts a learning process that relies solely on the portfolio's overall return, whereas the proposed extended reinforcement model also takes the risk and covariance of the investments into account. The experimental results illustrate that people reacted sensitively to...

  6. Reinforcement learning improves behaviour from evaluative feedback

    Science.gov (United States)

    Littman, Michael L.

    2015-05-01

    Reinforcement learning is a branch of machine learning concerned with using experience gained through interacting with the world and evaluative feedback to improve a system's ability to make behavioural decisions. It has been called the artificial intelligence problem in a microcosm because learning algorithms must act autonomously to perform well and achieve their goals. Partly driven by the increasing availability of rich data, recent years have seen exciting advances in the theory and practice of reinforcement learning, including developments in fundamental technical areas such as generalization, planning, exploration and empirical methodology, leading to increasing applicability to real-life problems.

  7. Learning to trade via direct reinforcement.

    Science.gov (United States)

    Moody, J; Saffell, M

    2001-01-01

    We present methods for optimizing portfolios, asset allocations, and trading systems based on direct reinforcement (DR). In this approach, investment decision-making is viewed as a stochastic control problem, and strategies are discovered directly. We present an adaptive algorithm called recurrent reinforcement learning (RRL) for discovering investment policies. The need to build forecasting models is eliminated, and better trading performance is obtained. The direct reinforcement approach differs from dynamic programming and reinforcement algorithms such as TD-learning and Q-learning, which attempt to estimate a value function for the control problem. We find that the RRL direct reinforcement framework enables a simpler problem representation, avoids Bellman's curse of dimensionality and offers compelling advantages in efficiency. We demonstrate how direct reinforcement can be used to optimize risk-adjusted investment returns (including the differential Sharpe ratio), while accounting for the effects of transaction costs. In extensive simulation work using real financial data, we find that our approach based on RRL produces better trading strategies than systems utilizing Q-learning (a value function method). Real-world applications include an intra-daily currency trader and a monthly asset allocation system for the S&P 500 Stock Index and T-Bills.

  8. Using a board game to reinforce learning.

    Science.gov (United States)

    Yoon, Bona; Rodriguez, Leslie; Faselis, Charles J; Liappis, Angelike P

    2014-03-01

    Experiential gaming strategies offer a variation on traditional learning. A board game was used to present synthesized content of fundamental catheter care concepts and reinforce evidence-based practices relevant to nursing. Board games are innovative educational tools that can enhance active learning. Copyright 2014, SLACK Incorporated.

  9. Embedded Incremental Feature Selection for Reinforcement Learning

    Science.gov (United States)

    2012-05-01

    Prior to this work, feature selection for reinforce- ment learning has focused on linear value function ap- proximation ( Kolter and Ng, 2009; Parr et al...InProceed- ings of the the 23rd International Conference on Ma- chine Learning, pages 449–456. Kolter , J. Z. and Ng, A. Y. (2009). Regularization and feature

  10. Online reinforcement learning control for aerospace systems

    NARCIS (Netherlands)

    Zhou, Y.

    2018-01-01

    Reinforcement Learning (RL) methods are relatively new in the field of aerospace guidance, navigation, and control. This dissertation aims to exploit RL methods to improve the autonomy and online learning of aerospace systems with respect to the a priori unknown system and environment, dynamical

  11. Reinforcement Learning in Continuous Action Spaces

    NARCIS (Netherlands)

    Hasselt, H. van; Wiering, M.A.

    2007-01-01

    Quite some research has been done on Reinforcement Learning in continuous environments, but the research on problems where the actions can also be chosen from a continuous space is much more limited. We present a new class of algorithms named Continuous Actor Critic Learning Automaton (CACLA)

  12. OWL model of multi-agent Smart-system of distance learning for people with vision disabilities

    Directory of Open Access Journals (Sweden)

    Galina A. Samigulina

    2017-01-01

    Full Text Available The aim of the study is to develop an ontological model of multiagent smart-system of distance learning for visually impaired people based on Java Agent Development Framework for obtaining high-quality engineering education in laboratories of join use on modern equipment.Materials and methods of research. In developing multi-agent smart-system of distance learning, using various agents based on cognitive, ontological, statistical and intellectual methods is important. It is more convenient to implement this task in the form of software using multi-agent approach and Java Agent Development Framework. The main advantages of the platform are stability of operation, clear interface, simplicity of creating agents and extensive user database. In multi-agent systems, the solution is obtained automatically as result of interaction of many independent, purposeful agents. Each agent can perform certain tasks and pursue specified goals. Intellectual multi-agent systems and practical applications in distance learning based on them are considered.Results. The structural diagram of functioning of smart system distance learning for visually impaired people using various agents based on the system approach and the multi-agent platform Java Agent Development Framework is developed. The complex approach of distance learning of visually impaired people for obtaining highquality engineering education in laboratories of joint use on modern equipment is offered.The ontological model of multi-agent smart-system with a detailed description of the functions of following agents is created: personal, manager, ontological, cognitive, statistical, intellectual, shared laboratory agent, health agent, assistant to the agent and state agent. These agents execute their individual functions and provide a quality environment for learning.Conclusion. Thus, the proposed smart-system of distance learning for visually impaired people can significantly improve effectiveness and

  13. Collective learning for the emergence of social norms in networked multiagent systems.

    Science.gov (United States)

    Yu, Chao; Zhang, Minjie; Ren, Fenghui

    2014-12-01

    Social norms such as social rules and conventions play a pivotal role in sustaining system order by regulating and controlling individual behaviors toward a global consensus in large-scale distributed systems. Systematic studies of efficient mechanisms that can facilitate the emergence of social norms enable us to build and design robust distributed systems, such as electronic institutions and norm-governed sensor networks. This paper studies the emergence of social norms via learning from repeated local interactions in networked multiagent systems. A collective learning framework, which imitates the opinion aggregation process in human decision making, is proposed to study the impact of agent local collective behaviors on the emergence of social norms in a number of different situations. In the framework, each agent interacts repeatedly with all of its neighbors. At each step, an agent first takes a best-response action toward each of its neighbors and then combines all of these actions into a final action using ensemble learning methods. Extensive experiments are carried out to evaluate the framework with respect to different network topologies, learning strategies, numbers of actions, influences of nonlearning agents, and so on. Experimental results reveal some significant insights into the manipulation and control of norm emergence in networked multiagent systems achieved through local collective behaviors.

  14. Value learning through reinforcement : The basics of dopamine and reinforcement learning

    NARCIS (Netherlands)

    Daw, N.D.; Tobler, P.N.; Glimcher, P.W.; Fehr, E.

    2013-01-01

    This chapter provides an overview of reinforcement learning and temporal difference learning and relates these topics to the firing properties of midbrain dopamine neurons. First, we review the RescorlaWagner learning rule and basic learning phenomena, such as blocking, which the rule explains. Then

  15. Reinforcement Learning in Autism Spectrum Disorder

    Directory of Open Access Journals (Sweden)

    Manuela Schuetze

    2017-11-01

    Full Text Available Early behavioral interventions are recognized as integral to standard care in autism spectrum disorder (ASD, and often focus on reinforcing desired behaviors (e.g., eye contact and reducing the presence of atypical behaviors (e.g., echoing others' phrases. However, efficacy of these programs is mixed. Reinforcement learning relies on neurocircuitry that has been reported to be atypical in ASD: prefrontal-sub-cortical circuits, amygdala, brainstem, and cerebellum. Thus, early behavioral interventions rely on neurocircuitry that may function atypically in at least a subset of individuals with ASD. Recent work has investigated physiological, behavioral, and neural responses to reinforcers to uncover differences in motivation and learning in ASD. We will synthesize this work to identify promising avenues for future research that ultimately can be used to enhance the efficacy of early intervention.

  16. Autonomous reinforcement learning with experience replay.

    Science.gov (United States)

    Wawrzyński, Paweł; Tanwani, Ajay Kumar

    2013-05-01

    This paper considers the issues of efficiency and autonomy that are required to make reinforcement learning suitable for real-life control tasks. A real-time reinforcement learning algorithm is presented that repeatedly adjusts the control policy with the use of previously collected samples, and autonomously estimates the appropriate step-sizes for the learning updates. The algorithm is based on the actor-critic with experience replay whose step-sizes are determined on-line by an enhanced fixed point algorithm for on-line neural network training. An experimental study with simulated octopus arm and half-cheetah demonstrates the feasibility of the proposed algorithm to solve difficult learning control problems in an autonomous way within reasonably short time. Copyright © 2012 Elsevier Ltd. All rights reserved.

  17. Reinforcement learning: Solving two case studies

    Science.gov (United States)

    Duarte, Ana Filipa; Silva, Pedro; dos Santos, Cristina Peixoto

    2012-09-01

    Reinforcement Learning algorithms offer interesting features for the control of autonomous systems, such as the ability to learn from direct interaction with the environment, and the use of a simple reward signalas opposed to the input-outputs pairsused in classic supervised learning. The reward signal indicates the success of failure of the actions executed by the agent in the environment. In this work, are described RL algorithmsapplied to two case studies: the Crawler robot and the widely known inverted pendulum. We explore RL capabilities to autonomously learn a basic locomotion pattern in the Crawler, andapproach the balancing problem of biped locomotion using the inverted pendulum.

  18. Concurrent Learning of Control in Multi agent Sequential Decision Tasks

    Science.gov (United States)

    2018-04-17

    Concurrent Learning of Control in Multi-agent Sequential Decision Tasks The overall objective of this project was to develop multi-agent reinforcement... learning (MARL) approaches for intelligent agents to autonomously learn distributed control policies in decentral- ized partially observable... learning of policies in Dec-POMDPs, established performance bounds, evaluated these algorithms both theoretically and empirically, The views

  19. Efficient abstraction selection in reinforcement learning

    NARCIS (Netherlands)

    Seijen, H. van; Whiteson, S.; Kester, L.

    2013-01-01

    This paper introduces a novel approach for abstraction selection in reinforcement learning problems modelled as factored Markov decision processes (MDPs), for which a state is described via a set of state components. In abstraction selection, an agent must choose an abstraction from a set of

  20. Multi-agent models of spatial cognition, learning and complex choice behavior in urban environments

    NARCIS (Netherlands)

    Arentze, Theo; Timmermans, Harry; Portugali, J.

    2006-01-01

    This chapter provides an overview of ongoing research projects in the DDSS research program at TUE related to multi-agents. Projects include (a) the use of multi-agent models and concepts of artificial intelligence to develop models of activity-travel behavior; (b) the use of a multi-agent model to

  1. A Two-Stage Multi-Agent Based Assessment Approach to Enhance Students' Learning Motivation through Negotiated Skills Assessment

    Science.gov (United States)

    Chadli, Abdelhafid; Bendella, Fatima; Tranvouez, Erwan

    2015-01-01

    In this paper we present an Agent-based evaluation approach in a context of Multi-agent simulation learning systems. Our evaluation model is based on a two stage assessment approach: (1) a Distributed skill evaluation combining agents and fuzzy sets theory; and (2) a Negotiation based evaluation of students' performance during a training…

  2. Reinforcement Learning Based Artificial Immune Classifier

    Directory of Open Access Journals (Sweden)

    Mehmet Karakose

    2013-01-01

    Full Text Available One of the widely used methods for classification that is a decision-making process is artificial immune systems. Artificial immune systems based on natural immunity system can be successfully applied for classification, optimization, recognition, and learning in real-world problems. In this study, a reinforcement learning based artificial immune classifier is proposed as a new approach. This approach uses reinforcement learning to find better antibody with immune operators. The proposed new approach has many contributions according to other methods in the literature such as effectiveness, less memory cell, high accuracy, speed, and data adaptability. The performance of the proposed approach is demonstrated by simulation and experimental results using real data in Matlab and FPGA. Some benchmark data and remote image data are used for experimental results. The comparative results with supervised/unsupervised based artificial immune system, negative selection classifier, and resource limited artificial immune classifier are given to demonstrate the effectiveness of the proposed new method.

  3. Social Influence as Reinforcement Learning

    Science.gov (United States)

    2016-01-13

    a brain region associated with motivation and reward learning. Further, individuals’ level of striatal activity in response to consensus tracks...experiment. Economics Letters, 2001. 71(3): p. 397-404. 14. Ledyard, J., Public goods: A survey of experimental research. Pub Econ , 1994.

  4. An Analysis on a Negotiation Model Based on Multiagent Systems with Symbiotic Learning and Evolution

    Science.gov (United States)

    Hossain, Md. Tofazzal

    This study explores an evolutionary analysis on a negotiation model based on Masbiole (Multiagent Systems with Symbiotic Learning and Evolution) which has been proposed as a new methodology of Multiagent Systems (MAS) based on symbiosis in the ecosystem. In Masbiole, agents evolve in consideration of not only their own benefits and losses, but also the benefits and losses of opponent agents. To aid effective application of Masbiole, we develop a competitive negotiation model where rigorous and advanced intelligent decision-making mechanisms are required for agents to achieve solutions. A Negotiation Protocol is devised aiming at developing a set of rules for agents' behavior during evolution. Simulations use a newly developed evolutionary computing technique, called Genetic Network Programming (GNP) which has the directed graph-type gene structure that can develop and design the required intelligent mechanisms for agents. In a typical scenario, competitive negotiation solutions are reached by concessions that are usually predetermined in the conventional MAS. In this model, however, not only concession is determined automatically by symbiotic evolution (making the system intelligent, automated, and efficient) but the solution also achieves Pareto optimal automatically.

  5. LDA merging and splitting with applications to multiagent cooperative learning and system alteration.

    Science.gov (United States)

    Pang, Shaoning; Ban, Tao; Kadobayashi, Youki; Kasabov, Nikola K

    2012-04-01

    To adapt linear discriminant analysis (LDA) to real-world applications, there is a pressing need to equip it with an incremental learning ability to integrate knowledge presented by one-pass data streams, a functionality to join multiple LDA models to make the knowledge sharing between independent learning agents more efficient, and a forgetting functionality to avoid reconstruction of the overall discriminant eigenspace caused by some irregular changes. To this end, we introduce two adaptive LDA learning methods: LDA merging and LDA splitting. These provide the benefits of ability of online learning with one-pass data streams, retained class separability identical to the batch learning method, high efficiency for knowledge sharing due to condensed knowledge representation by the eigenspace model, and more preferable time and storage costs than traditional approaches under common application conditions. These properties are validated by experiments on a benchmark face image data set. By a case study on the application of the proposed method to multiagent cooperative learning and system alternation of a face recognition system, we further clarified the adaptability of the proposed methods to complex dynamic learning tasks.

  6. Reinforcement Learning and Savings Behavior.

    Science.gov (United States)

    Choi, James J; Laibson, David; Madrian, Brigitte C; Metrick, Andrew

    2009-12-01

    We show that individual investors over-extrapolate from their personal experience when making savings decisions. Investors who experience particularly rewarding outcomes from saving in their 401(k)-a high average and/or low variance return-increase their 401(k) savings rate more than investors who have less rewarding experiences with saving. This finding is not driven by aggregate time-series shocks, income effects, rational learning about investing skill, investor fixed effects, or time-varying investor-level heterogeneity that is correlated with portfolio allocations to stock, bond, and cash asset classes. We discuss implications for the equity premium puzzle and interventions aimed at improving household financial outcomes.

  7. Reinforcement learning for microgrid energy management

    International Nuclear Information System (INIS)

    Kuznetsova, Elizaveta; Li, Yan-Fu; Ruiz, Carlos; Zio, Enrico; Ault, Graham; Bell, Keith

    2013-01-01

    We consider a microgrid for energy distribution, with a local consumer, a renewable generator (wind turbine) and a storage facility (battery), connected to the external grid via a transformer. We propose a 2 steps-ahead reinforcement learning algorithm to plan the battery scheduling, which plays a key role in the achievement of the consumer goals. The underlying framework is one of multi-criteria decision-making by an individual consumer who has the goals of increasing the utilization rate of the battery during high electricity demand (so as to decrease the electricity purchase from the external grid) and increasing the utilization rate of the wind turbine for local use (so as to increase the consumer independence from the external grid). Predictions of available wind power feed the reinforcement learning algorithm for selecting the optimal battery scheduling actions. The embedded learning mechanism allows to enhance the consumer knowledge about the optimal actions for battery scheduling under different time-dependent environmental conditions. The developed framework gives the capability to intelligent consumers to learn the stochastic environment and make use of the experience to select optimal energy management actions. - Highlights: • A consumer exploits a 2 steps-ahead reinforcement learning for battery scheduling. • The Q-learning based mechanism is fed by the predictions of available wind power. • Wind speed state evolutions are modeled with a Markov chain model. • Optimal scheduling actions are learned through the occurrence of similar scenarios. • The consumer manifests a continuous enhance of his knowledge about optimal actions

  8. Reinforcement Learning and Savings Behavior*

    Science.gov (United States)

    Choi, James J.; Laibson, David; Madrian, Brigitte C.; Metrick, Andrew

    2009-01-01

    We show that individual investors over-extrapolate from their personal experience when making savings decisions. Investors who experience particularly rewarding outcomes from saving in their 401(k)—a high average and/or low variance return—increase their 401(k) savings rate more than investors who have less rewarding experiences with saving. This finding is not driven by aggregate time-series shocks, income effects, rational learning about investing skill, investor fixed effects, or time-varying investor-level heterogeneity that is correlated with portfolio allocations to stock, bond, and cash asset classes. We discuss implications for the equity premium puzzle and interventions aimed at improving household financial outcomes. PMID:20352013

  9. Online constrained model-based reinforcement learning

    CSIR Research Space (South Africa)

    Van Niekerk, B

    2017-08-01

    Full Text Available Constrained Model-based Reinforcement Learning Benjamin van Niekerk School of Computer Science University of the Witwatersrand South Africa Andreas Damianou∗ Amazon.com Cambridge, UK Benjamin Rosman Council for Scientific and Industrial Research, and School... MULTIPLE SHOOTING Using direct multiple shooting (Bock and Plitt, 1984), problem (1) can be transformed into a structured non- linear program (NLP). First, the time horizon [t0, t0 + T ] is partitioned into N equal subintervals [tk, tk+1] for k = 0...

  10. Multi-Agent Inference in Social Networks: A Finite Population Learning Approach.

    Science.gov (United States)

    Fan, Jianqing; Tong, Xin; Zeng, Yao

    When people in a society want to make inference about some parameter, each person may want to use data collected by other people. Information (data) exchange in social networks is usually costly, so to make reliable statistical decisions, people need to trade off the benefits and costs of information acquisition. Conflicts of interests and coordination problems will arise in the process. Classical statistics does not consider people's incentives and interactions in the data collection process. To address this imperfection, this work explores multi-agent Bayesian inference problems with a game theoretic social network model. Motivated by our interest in aggregate inference at the societal level, we propose a new concept, finite population learning , to address whether with high probability, a large fraction of people in a given finite population network can make "good" inference. Serving as a foundation, this concept enables us to study the long run trend of aggregate inference quality as population grows.

  11. Enriching behavioral ecology with reinforcement learning methods.

    Science.gov (United States)

    Frankenhuis, Willem E; Panchanathan, Karthik; Barto, Andrew G

    2018-02-13

    This article focuses on the division of labor between evolution and development in solving sequential, state-dependent decision problems. Currently, behavioral ecologists tend to use dynamic programming methods to study such problems. These methods are successful at predicting animal behavior in a variety of contexts. However, they depend on a distinct set of assumptions. Here, we argue that behavioral ecology will benefit from drawing more than it currently does on a complementary collection of tools, called reinforcement learning methods. These methods allow for the study of behavior in highly complex environments, which conventional dynamic programming methods do not feasibly address. In addition, reinforcement learning methods are well-suited to studying how biological mechanisms solve developmental and learning problems. For instance, we can use them to study simple rules that perform well in complex environments. Or to investigate under what conditions natural selection favors fixed, non-plastic traits (which do not vary across individuals), cue-driven-switch plasticity (innate instructions for adaptive behavioral development based on experience), or developmental selection (the incremental acquisition of adaptive behavior based on experience). If natural selection favors developmental selection, which includes learning from environmental feedback, we can also make predictions about the design of reward systems. Our paper is written in an accessible manner and for a broad audience, though we believe some novel insights can be drawn from our discussion. We hope our paper will help advance the emerging bridge connecting the fields of behavioral ecology and reinforcement learning. Copyright © 2018 The Authors. Published by Elsevier B.V. All rights reserved.

  12. SCAFFOLDINGAND REINFORCEMENT: USING DIGITAL LOGBOOKS IN LEARNING VOCABULARY

    OpenAIRE

    Khalifa, Salma Hasan Almabrouk; Shabdin, Ahmad Affendi

    2016-01-01

    Reinforcement and scaffolding are tested approaches to enhance learning achievements. Keeping a record of the learning process as well as the new learned words functions as scaffolding to help learners build a comprehensive vocabulary. Similarly, repetitive learning of new words reinforces permanent learning for long-term memory. Paper-based logbooks may prove to be good records of the learning process, but if learners use digital logbooks, the results may be even better. Digital logbooks wit...

  13. Human demonstrations for fast and safe exploration in reinforcement learning

    NARCIS (Netherlands)

    Schonebaum, G.K.; Junell, J.L.; van Kampen, E.

    2017-01-01

    Reinforcement learning is a promising framework for controlling complex vehicles with a high level of autonomy, since it does not need a dynamic model of the vehicle, and it is able to adapt to changing conditions. When learning from scratch, the performance of a reinforcement learning controller

  14. Reinforcement learning account of network reciprocity.

    Science.gov (United States)

    Ezaki, Takahiro; Masuda, Naoki

    2017-01-01

    Evolutionary game theory predicts that cooperation in social dilemma games is promoted when agents are connected as a network. However, when networks are fixed over time, humans do not necessarily show enhanced mutual cooperation. Here we show that reinforcement learning (specifically, the so-called Bush-Mosteller model) approximately explains the experimentally observed network reciprocity and the lack thereof in a parameter region spanned by the benefit-to-cost ratio and the node's degree. Thus, we significantly extend previously obtained numerical results.

  15. Reinforcement learning account of network reciprocity.

    Directory of Open Access Journals (Sweden)

    Takahiro Ezaki

    Full Text Available Evolutionary game theory predicts that cooperation in social dilemma games is promoted when agents are connected as a network. However, when networks are fixed over time, humans do not necessarily show enhanced mutual cooperation. Here we show that reinforcement learning (specifically, the so-called Bush-Mosteller model approximately explains the experimentally observed network reciprocity and the lack thereof in a parameter region spanned by the benefit-to-cost ratio and the node's degree. Thus, we significantly extend previously obtained numerical results.

  16. Ensemble Network Architecture for Deep Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Xi-liang Chen

    2018-01-01

    Full Text Available The popular deep Q learning algorithm is known to be instability because of the Q-value’s shake and overestimation action values under certain conditions. These issues tend to adversely affect their performance. In this paper, we develop the ensemble network architecture for deep reinforcement learning which is based on value function approximation. The temporal ensemble stabilizes the training process by reducing the variance of target approximation error and the ensemble of target values reduces the overestimate and makes better performance by estimating more accurate Q-value. Our results show that this architecture leads to statistically significant better value evaluation and more stable and better performance on several classical control tasks at OpenAI Gym environment.

  17. Optimizing Chemical Reactions with Deep Reinforcement Learning.

    Science.gov (United States)

    Zhou, Zhenpeng; Li, Xiaocheng; Zare, Richard N

    2017-12-27

    Deep reinforcement learning was employed to optimize chemical reactions. Our model iteratively records the results of a chemical reaction and chooses new experimental conditions to improve the reaction outcome. This model outperformed a state-of-the-art blackbox optimization algorithm by using 71% fewer steps on both simulations and real reactions. Furthermore, we introduced an efficient exploration strategy by drawing the reaction conditions from certain probability distributions, which resulted in an improvement on regret from 0.062 to 0.039 compared with a deterministic policy. Combining the efficient exploration policy with accelerated microdroplet reactions, optimal reaction conditions were determined in 30 min for the four reactions considered, and a better understanding of the factors that control microdroplet reactions was reached. Moreover, our model showed a better performance after training on reactions with similar or even dissimilar underlying mechanisms, which demonstrates its learning ability.

  18. Vicarious reinforcement learning signals when instructing others.

    Science.gov (United States)

    Apps, Matthew A J; Lesage, Elise; Ramnani, Narender

    2015-02-18

    Reinforcement learning (RL) theory posits that learning is driven by discrepancies between the predicted and actual outcomes of actions (prediction errors [PEs]). In social environments, learning is often guided by similar RL mechanisms. For example, teachers monitor the actions of students and provide feedback to them. This feedback evokes PEs in students that guide their learning. We report the first study that investigates the neural mechanisms that underpin RL signals in the brain of a teacher. Neurons in the anterior cingulate cortex (ACC) signal PEs when learning from the outcomes of one's own actions but also signal information when outcomes are received by others. Does a teacher's ACC signal PEs when monitoring a student's learning? Using fMRI, we studied brain activity in human subjects (teachers) as they taught a confederate (student) action-outcome associations by providing positive or negative feedback. We examined activity time-locked to the students' responses, when teachers infer student predictions and know actual outcomes. We fitted a RL-based computational model to the behavior of the student to characterize their learning, and examined whether a teacher's ACC signals when a student's predictions are wrong. In line with our hypothesis, activity in the teacher's ACC covaried with the PE values in the model. Additionally, activity in the teacher's insula and ventromedial prefrontal cortex covaried with the predicted value according to the student. Our findings highlight that the ACC signals PEs vicariously for others' erroneous predictions, when monitoring and instructing their learning. These results suggest that RL mechanisms, processed vicariously, may underpin and facilitate teaching behaviors. Copyright © 2015 Apps et al.

  19. Optimizing microstimulation using a reinforcement learning framework.

    Science.gov (United States)

    Brockmeier, Austin J; Choi, John S; Distasio, Marcello M; Francis, Joseph T; Príncipe, José C

    2011-01-01

    The ability to provide sensory feedback is desired to enhance the functionality of neuroprosthetics. Somatosensory feedback provides closed-loop control to the motor system, which is lacking in feedforward neuroprosthetics. In the case of existing somatosensory function, a template of the natural response can be used as a template of desired response elicited by electrical microstimulation. In the case of no initial training data, microstimulation parameters that produce responses close to the template must be selected in an online manner. We propose using reinforcement learning as a framework to balance the exploration of the parameter space and the continued selection of promising parameters for further stimulation. This approach avoids an explicit model of the neural response from stimulation. We explore a preliminary architecture--treating the task as a k-armed bandit--using offline data recorded for natural touch and thalamic microstimulation, and we examine the methods efficiency in exploring the parameter space while concentrating on promising parameter forms. The best matching stimulation parameters, from k = 68 different forms, are selected by the reinforcement learning algorithm consistently after 334 realizations.

  20. Reinforcement Learning for Ramp Control: An Analysis of Learning Parameters

    Directory of Open Access Journals (Sweden)

    Chao Lu

    2016-08-01

    Full Text Available Reinforcement Learning (RL has been proposed to deal with ramp control problems under dynamic traffic conditions; however, there is a lack of sufficient research on the behaviour and impacts of different learning parameters. This paper describes a ramp control agent based on the RL mechanism and thoroughly analyzed the influence of three learning parameters; namely, learning rate, discount rate and action selection parameter on the algorithm performance. Two indices for the learning speed and convergence stability were used to measure the algorithm performance, based on which a series of simulation-based experiments were designed and conducted by using a macroscopic traffic flow model. Simulation results showed that, compared with the discount rate, the learning rate and action selection parameter made more remarkable impacts on the algorithm performance. Based on the analysis, some suggestionsabout how to select suitable parameter values that can achieve a superior performance were provided.

  1. Reusable Reinforcement Learning via Shallow Trails.

    Science.gov (United States)

    Yu, Yang; Chen, Shi-Yong; Da, Qing; Zhou, Zhi-Hua

    2018-06-01

    Reinforcement learning has shown great success in helping learning agents accomplish tasks autonomously from environment interactions. Meanwhile in many real-world applications, an agent needs to accomplish not only a fixed task but also a range of tasks. For this goal, an agent can learn a metapolicy over a set of training tasks that are drawn from an underlying distribution. By maximizing the total reward summed over all the training tasks, the metapolicy can then be reused in accomplishing test tasks from the same distribution. However, in practice, we face two major obstacles to train and reuse metapolicies well. First, how to identify tasks that are unrelated or even opposite with each other, in order to avoid their mutual interference in the training. Second, how to characterize task features, according to which a metapolicy can be reused. In this paper, we propose the MetA-Policy LEarning (MAPLE) approach that overcomes the two difficulties by introducing the shallow trail. It probes a task by running a roughly trained policy. Using the rewards of the shallow trail, MAPLE automatically groups similar tasks. Moreover, when the task parameters are unknown, the rewards of the shallow trail also serve as task features. Empirical studies on several controlling tasks verify that MAPLE can train metapolicies well and receives high reward on test tasks.

  2. Framework for robot skill learning using reinforcement learning

    Science.gov (United States)

    Wei, Yingzi; Zhao, Mingyang

    2003-09-01

    Robot acquiring skill is a process similar to human skill learning. Reinforcement learning (RL) is an on-line actor critic method for a robot to develop its skill. The reinforcement function has become the critical component for its effect of evaluating the action and guiding the learning process. We present an augmented reward function that provides a new way for RL controller to incorporate prior knowledge and experience into the RL controller. Also, the difference form of augmented reward function is considered carefully. The additional reward beyond conventional reward will provide more heuristic information for RL. In this paper, we present a strategy for the task of complex skill learning. Automatic robot shaping policy is to dissolve the complex skill into a hierarchical learning process. The new form of value function is introduced to attain smooth motion switching swiftly. We present a formal, but practical, framework for robot skill learning and also illustrate with an example the utility of method for learning skilled robot control on line.

  3. Punishment Insensitivity and Impaired Reinforcement Learning in Preschoolers

    Science.gov (United States)

    Briggs-Gowan, Margaret J.; Nichols, Sara R.; Voss, Joel; Zobel, Elvira; Carter, Alice S.; McCarthy, Kimberly J.; Pine, Daniel S.; Blair, James; Wakschlag, Lauren S.

    2014-01-01

    Background: Youth and adults with psychopathic traits display disrupted reinforcement learning. Advances in measurement now enable examination of this association in preschoolers. The current study examines relations between reinforcement learning in preschoolers and parent ratings of reduced responsiveness to socialization, conceptualized as a…

  4. Continuous residual reinforcement learning for traffic signal control optimization

    NARCIS (Netherlands)

    Aslani, Mohammad; Seipel, Stefan; Wiering, Marco

    2018-01-01

    Traffic signal control can be naturally regarded as a reinforcement learning problem. Unfortunately, it is one of the most difficult classes of reinforcement learning problems owing to its large state space. A straightforward approach to address this challenge is to control traffic signals based on

  5. Reinforcement learning in continuous state and action spaces

    NARCIS (Netherlands)

    H. P. van Hasselt (Hado); M.A. Wiering; M. van Otterlo

    2012-01-01

    textabstractMany traditional reinforcement-learning algorithms have been designed for problems with small finite state and action spaces. Learning in such discrete problems can been difficult, due to noise and delayed reinforcements. However, many real-world problems have continuous state or action

  6. Learning and Sharing Technology in Informal Contexts. A Multiagent-Based Ontological Approach

    Directory of Open Access Journals (Sweden)

    Dino Borri

    2014-05-01

    Full Text Available An increasing debate is growing today, in both academic and research-in-action contexts, about the roles of new and traditional technologies in raising knowledge of agents involved, as well as in boosting an effective development of communities. The last century has been largely dominated by capital-intensive technologies, impacting large and populated areas. From the late 1990s up to the present days, due to social, financial, environmental concerns, new low-impact, local-born, little to medium-scale experiences have been challenging large technologies, with interesting results. The importance of such experiences seems to lay on the abilities and knowledge of local populations, which are quite difficult to emerge as formal methodologies and attain recognizable levels of generalization and sharing. Yet the effectiveness of local-based technologies is being increasingly documented, often succeeding in cases where more formal technologies had previously failed. The EU-funded ANTINOMOS project has largely dealt with local-community knowledge enhancing and managing in the water sector management, aiming at creating a real learning environment for the sharing and the active generation of knowledge through mutual synergies. In this paper, the above subject is discussed and carried out with a cross-disciplinary, cross-scale, multi-agent approach, considering the different forms of local knowledge and language involved.

  7. Tank War Using Online Reinforcement Learning

    DEFF Research Database (Denmark)

    Toftgaard Andersen, Kresten; Zeng, Yifeng; Dahl Christensen, Dennis

    2009-01-01

    Real-Time Strategy(RTS) games provide a challenging platform to implement online reinforcement learning(RL) techniques in a real application. Computer as one player monitors opponents'(human or other computers) strategies and then updates its own policy using RL methods. In this paper, we propose...... a multi-layer framework for implementing the online RL in a RTS game. The framework significantly reduces the RL computational complexity by decomposing the state space in a hierarchical manner. We implement the RTS game - Tank General, and perform a thorough test on the proposed framework. The results...... show the effectiveness of our proposed framework and shed light on relevant issues on using the RL in RTS games....

  8. Reinforcement learning in complementarity game and population dynamics.

    Science.gov (United States)

    Jost, Jürgen; Li, Wei

    2014-02-01

    We systematically test and compare different reinforcement learning schemes in a complementarity game [J. Jost and W. Li, Physica A 345, 245 (2005)] played between members of two populations. More precisely, we study the Roth-Erev, Bush-Mosteller, and SoftMax reinforcement learning schemes. A modified version of Roth-Erev with a power exponent of 1.5, as opposed to 1 in the standard version, performs best. We also compare these reinforcement learning strategies with evolutionary schemes. This gives insight into aspects like the issue of quick adaptation as opposed to systematic exploration or the role of learning rates.

  9. A Day-to-Day Route Choice Model Based on Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Fangfang Wei

    2014-01-01

    Full Text Available Day-to-day traffic dynamics are generated by individual traveler’s route choice and route adjustment behaviors, which are appropriate to be researched by using agent-based model and learning theory. In this paper, we propose a day-to-day route choice model based on reinforcement learning and multiagent simulation. Travelers’ memory, learning rate, and experience cognition are taken into account. Then the model is verified and analyzed. Results show that the network flow can converge to user equilibrium (UE if travelers can remember all the travel time they have experienced, but which is not necessarily the case under limited memory; learning rate can strengthen the flow fluctuation, but memory leads to the contrary side; moreover, high learning rate results in the cyclical oscillation during the process of flow evolution. Finally, both the scenarios of link capacity degradation and random link capacity are used to illustrate the model’s applications. Analyses and applications of our model demonstrate the model is reasonable and useful for studying the day-to-day traffic dynamics.

  10. Multiobjective Reinforcement Learning for Traffic Signal Control Using Vehicular Ad Hoc Network

    Directory of Open Access Journals (Sweden)

    Houli Duan

    2010-01-01

    Full Text Available We propose a new multiobjective control algorithm based on reinforcement learning for urban traffic signal control, named multi-RL. A multiagent structure is used to describe the traffic system. A vehicular ad hoc network is used for the data exchange among agents. A reinforcement learning algorithm is applied to predict the overall value of the optimization objective given vehicles' states. The policy which minimizes the cumulative value of the optimization objective is regarded as the optimal one. In order to make the method adaptive to various traffic conditions, we also introduce a multiobjective control scheme in which the optimization objective is selected adaptively to real-time traffic states. The optimization objectives include the vehicle stops, the average waiting time, and the maximum queue length of the next intersection. In addition, we also accommodate a priority control to the buses and the emergency vehicles through our model. The simulation results indicated that our algorithm could perform more efficiently than traditional traffic light control methods.

  11. Solution to reinforcement learning problems with artificial potential field

    Institute of Scientific and Technical Information of China (English)

    XIE Li-juan; XIE Guang-rong; CHEN Huan-wen; LI Xiao-li

    2008-01-01

    A novel method was designed to solve reinforcement learning problems with artificial potential field. Firstly a reinforcement learning problem was transferred to a path planning problem by using artificial potential field(APF), which was a very appropriate method to model a reinforcement learning problem. Secondly, a new APF algorithm was proposed to overcome the local minimum problem in the potential field methods with a virtual water-flow concept. The performance of this new method was tested by a gridworld problem named as key and door maze. The experimental results show that within 45 trials, good and deterministic policies are found in almost all simulations. In comparison with WIERING's HQ-learning system which needs 20 000 trials for stable solution, the proposed new method can obtain optimal and stable policy far more quickly than HQ-learning. Therefore, the new method is simple and effective to give an optimal solution to the reinforcement learning problem.

  12. Switching Reinforcement Learning for Continuous Action Space

    Science.gov (United States)

    Nagayoshi, Masato; Murao, Hajime; Tamaki, Hisashi

    Reinforcement Learning (RL) attracts much attention as a technique of realizing computational intelligence such as adaptive and autonomous decentralized systems. In general, however, it is not easy to put RL into practical use. This difficulty includes a problem of designing a suitable action space of an agent, i.e., satisfying two requirements in trade-off: (i) to keep the characteristics (or structure) of an original search space as much as possible in order to seek strategies that lie close to the optimal, and (ii) to reduce the search space as much as possible in order to expedite the learning process. In order to design a suitable action space adaptively, we propose switching RL model to mimic a process of an infant's motor development in which gross motor skills develop before fine motor skills. Then, a method for switching controllers is constructed by introducing and referring to the “entropy”. Further, through computational experiments by using robot navigation problems with one and two-dimensional continuous action space, the validity of the proposed method has been confirmed.

  13. Tunnel Ventilation Control Using Reinforcement Learning Methodology

    Science.gov (United States)

    Chu, Baeksuk; Kim, Dongnam; Hong, Daehie; Park, Jooyoung; Chung, Jin Taek; Kim, Tae-Hyung

    The main purpose of tunnel ventilation system is to maintain CO pollutant concentration and VI (visibility index) under an adequate level to provide drivers with comfortable and safe driving environment. Moreover, it is necessary to minimize power consumption used to operate ventilation system. To achieve the objectives, the control algorithm used in this research is reinforcement learning (RL) method. RL is a goal-directed learning of a mapping from situations to actions without relying on exemplary supervision or complete models of the environment. The goal of RL is to maximize a reward which is an evaluative feedback from the environment. In the process of constructing the reward of the tunnel ventilation system, two objectives listed above are included, that is, maintaining an adequate level of pollutants and minimizing power consumption. RL algorithm based on actor-critic architecture and gradient-following algorithm is adopted to the tunnel ventilation system. The simulations results performed with real data collected from existing tunnel ventilation system and real experimental verification are provided in this paper. It is confirmed that with the suggested controller, the pollutant level inside the tunnel was well maintained under allowable limit and the performance of energy consumption was improved compared to conventional control scheme.

  14. Flexible Heuristic Dynamic Programming for Reinforcement Learning in Quadrotors

    NARCIS (Netherlands)

    Helmer, Alexander; de Visser, C.C.; van Kampen, E.

    2018-01-01

    Reinforcement learning is a paradigm for learning decision-making tasks from interaction with the environment. Function approximators solve a part of the curse of dimensionality when learning in high-dimensional state and/or action spaces. It can be a time-consuming process to learn a good policy in

  15. Episodic reinforcement learning control approach for biped walking

    Directory of Open Access Journals (Sweden)

    Katić Duško

    2012-01-01

    Full Text Available This paper presents a hybrid dynamic control approach to the realization of humanoid biped robotic walk, focusing on the policy gradient episodic reinforcement learning with fuzzy evaluative feedback. The proposed structure of controller involves two feedback loops: a conventional computed torque controller and an episodic reinforcement learning controller. The reinforcement learning part includes fuzzy information about Zero-Moment- Point errors. Simulation tests using a medium-size 36-DOF humanoid robot MEXONE were performed to demonstrate the effectiveness of our method.

  16. Cooperative learning neural network output feedback control of uncertain nonlinear multi-agent systems under directed topologies

    Science.gov (United States)

    Wang, W.; Wang, D.; Peng, Z. H.

    2017-09-01

    Without assuming that the communication topologies among the neural network (NN) weights are to be undirected and the states of each agent are measurable, the cooperative learning NN output feedback control is addressed for uncertain nonlinear multi-agent systems with identical structures in strict-feedback form. By establishing directed communication topologies among NN weights to share their learned knowledge, NNs with cooperative learning laws are employed to identify the uncertainties. By designing NN-based κ-filter observers to estimate the unmeasurable states, a new cooperative learning output feedback control scheme is proposed to guarantee that the system outputs can track nonidentical reference signals with bounded tracking errors. A simulation example is given to demonstrate the effectiveness of the theoretical results.

  17. Lung Nodule Detection via Deep Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Issa Ali

    2018-04-01

    Full Text Available Lung cancer is the most common cause of cancer-related death globally. As a preventive measure, the United States Preventive Services Task Force (USPSTF recommends annual screening of high risk individuals with low-dose computed tomography (CT. The resulting volume of CT scans from millions of people will pose a significant challenge for radiologists to interpret. To fill this gap, computer-aided detection (CAD algorithms may prove to be the most promising solution. A crucial first step in the analysis of lung cancer screening results using CAD is the detection of pulmonary nodules, which may represent early-stage lung cancer. The objective of this work is to develop and validate a reinforcement learning model based on deep artificial neural networks for early detection of lung nodules in thoracic CT images. Inspired by the AlphaGo system, our deep learning algorithm takes a raw CT image as input and views it as a collection of states, and output a classification of whether a nodule is present or not. The dataset used to train our model is the LIDC/IDRI database hosted by the lung nodule analysis (LUNA challenge. In total, there are 888 CT scans with annotations based on agreement from at least three out of four radiologists. As a result, there are 590 individuals having one or more nodules, and 298 having none. Our training results yielded an overall accuracy of 99.1% [sensitivity 99.2%, specificity 99.1%, positive predictive value (PPV 99.1%, negative predictive value (NPV 99.2%]. In our test, the results yielded an overall accuracy of 64.4% (sensitivity 58.9%, specificity 55.3%, PPV 54.2%, and NPV 60.0%. These early results show promise in solving the major issue of false positives in CT screening of lung nodules, and may help to save unnecessary follow-up tests and expenditures.

  18. Neural Basis of Reinforcement Learning and Decision Making

    Science.gov (United States)

    Lee, Daeyeol; Seo, Hyojung; Jung, Min Whan

    2012-01-01

    Reinforcement learning is an adaptive process in which an animal utilizes its previous experience to improve the outcomes of future choices. Computational theories of reinforcement learning play a central role in the newly emerging areas of neuroeconomics and decision neuroscience. In this framework, actions are chosen according to their value functions, which describe how much future reward is expected from each action. Value functions can be adjusted not only through reward and penalty, but also by the animal’s knowledge of its current environment. Studies have revealed that a large proportion of the brain is involved in representing and updating value functions and using them to choose an action. However, how the nature of a behavioral task affects the neural mechanisms of reinforcement learning remains incompletely understood. Future studies should uncover the principles by which different computational elements of reinforcement learning are dynamically coordinated across the entire brain. PMID:22462543

  19. applying reinforcement learning to the weapon assignment problem

    African Journals Online (AJOL)

    ismith

    Carlo (MC) control algorithm with exploring starts (MCES), and an off-policy ..... closest to the threat should fire (that weapon also had the highest probability to ... Monte Carlo ..... “Reinforcement learning: Theory, methods and application to.

  20. Exploiting Best-Match Equations for Efficient Reinforcement Learning

    NARCIS (Netherlands)

    van Seijen, Harm; Whiteson, Shimon; van Hasselt, Hado; Wiering, Marco

    This article presents and evaluates best-match learning, a new approach to reinforcement learning that trades off the sample efficiency of model-based methods with the space efficiency of model-free methods. Best-match learning works by approximating the solution to a set of best-match equations,

  1. Learning Science in Small Multi-Age Groups: The Role of Age Composition

    Science.gov (United States)

    Kallery, Maria; Loupidou, Thomais

    2016-01-01

    The present study examines how the overall cognitive achievements in science of the younger children in a class where the students work in small multi-age groups are influenced by the number of older children in the groups. The context of the study was early-years education. The study has two parts: The first part involved classes attended by…

  2. Safe Exploration of State and Action Spaces in Reinforcement Learning

    OpenAIRE

    Garcia, Javier; Fernandez, Fernando

    2014-01-01

    In this paper, we consider the important problem of safe exploration in reinforcement learning. While reinforcement learning is well-suited to domains with complex transition dynamics and high-dimensional state-action spaces, an additional challenge is posed by the need for safe and efficient exploration. Traditional exploration techniques are not particularly useful for solving dangerous tasks, where the trial and error process may lead to the selection of actions whose execution in some sta...

  3. Instructional control of reinforcement learning: a behavioral and neurocomputational investigation.

    Science.gov (United States)

    Doll, Bradley B; Jacobs, W Jake; Sanfey, Alan G; Frank, Michael J

    2009-11-24

    Humans learn how to behave directly through environmental experience and indirectly through rules and instructions. Behavior analytic research has shown that instructions can control behavior, even when such behavior leads to sub-optimal outcomes (Hayes, S. (Ed.). 1989. Rule-governed behavior: cognition, contingencies, and instructional control. Plenum Press.). Here we examine the control of behavior through instructions in a reinforcement learning task known to depend on striatal dopaminergic function. Participants selected between probabilistically reinforced stimuli, and were (incorrectly) told that a specific stimulus had the highest (or lowest) reinforcement probability. Despite experience to the contrary, instructions drove choice behavior. We present neural network simulations that capture the interactions between instruction-driven and reinforcement-driven behavior via two potential neural circuits: one in which the striatum is inaccurately trained by instruction representations coming from prefrontal cortex/hippocampus (PFC/HC), and another in which the striatum learns the environmentally based reinforcement contingencies, but is "overridden" at decision output. Both models capture the core behavioral phenomena but, because they differ fundamentally on what is learned, make distinct predictions for subsequent behavioral and neuroimaging experiments. Finally, we attempt to distinguish between the proposed computational mechanisms governing instructed behavior by fitting a series of abstract "Q-learning" and Bayesian models to subject data. The best-fitting model supports one of the neural models, suggesting the existence of a "confirmation bias" in which the PFC/HC system trains the reinforcement system by amplifying outcomes that are consistent with instructions while diminishing inconsistent outcomes.

  4. A Parent's Guide to Playground Safety, [and] The Multiage Classroom: A Guide for Parents, [and] Multiple Intelligences: Different Ways of Learning. ACEI Speaks Series.

    Science.gov (United States)

    Frost, Joe L.; And Others

    Three brochures for parents are presented. The first lists potential playground hazards and suggestions for improving playgrounds. The second describes benefits of the multiage classroom, comparing such a classroom with a traditional, single-grade class. The third brochure describes verbal, logical, visual, musical, and physical learning styles…

  5. An Online Q-learning Based Multi-Agent LFC for a Multi-Area Multi-Source Power System Including Distributed Energy Resources

    Directory of Open Access Journals (Sweden)

    H. Shayeghi

    2017-12-01

    Full Text Available This paper presents an online two-stage Q-learning based multi-agent (MA controller for load frequency control (LFC in an interconnected multi-area multi-source power system integrated with distributed energy resources (DERs. The proposed control strategy consists of two stages. The first stage is employed a PID controller which its parameters are designed using sine cosine optimization (SCO algorithm and are fixed. The second one is a reinforcement learning (RL based supplementary controller that has a flexible structure and improves the output of the first stage adaptively based on the system dynamical behavior. Due to the use of RL paradigm integrated with PID controller in this strategy, it is called RL-PID controller. The primary motivation for the integration of RL technique with PID controller is to make the existing local controllers in the industry compatible to reduce the control efforts and system costs. This novel control strategy combines the advantages of the PID controller with adaptive behavior of MA to achieve the desired level of robust performance under different kind of uncertainties caused by stochastically power generation of DERs, plant operational condition changes, and physical nonlinearities of the system. The suggested decentralized controller is composed of the autonomous intelligent agents, who learn the optimal control policy from interaction with the system. These agents update their knowledge about the system dynamics continuously to achieve a good frequency oscillation damping under various severe disturbances without any knowledge of them. It leads to an adaptive control structure to solve LFC problem in the multi-source power system with stochastic DERs. The results of RL-PID controller in comparison to the traditional PID and fuzzy-PID controllers is verified in a multi-area power system integrated with DERs through some performance indices.

  6. Adversarial Reinforcement Learning in a Cyber Security Simulation}

    OpenAIRE

    Elderman, Richard; Pater, Leon; Thie, Albert; Drugan, Madalina; Wiering, Marco

    2017-01-01

    This paper focuses on cyber-security simulations in networks modeled as a Markov game with incomplete information and stochastic elements. The resulting game is an adversarial sequential decision making problem played with two agents, the attacker and defender. The two agents pit one reinforcement learning technique, like neural networks, Monte Carlo learning and Q-learning, against each other and examine their effectiveness against learning opponents. The results showed that Monte Carlo lear...

  7. Game-theoretic learning and distributed optimization in memoryless multi-agent systems

    CERN Document Server

    Tatarenko, Tatiana

    2017-01-01

    This book presents new efficient methods for optimization in realistic large-scale, multi-agent systems. These methods do not require the agents to have the full information about the system, but instead allow them to make their local decisions based only on the local information, possibly obtained during scommunication with their local neighbors. The book, primarily aimed at researchers in optimization and control, considers three different information settings in multi-agent systems: oracle-based, communication-based, and payoff-based. For each of these information types, an efficient optimization algorithm is developed, which leads the system to an optimal state. The optimization problems are set without such restrictive assumptions as convexity of the objective functions, complicated communication topologies, closed-form expressions for costs and utilities, and finiteness of the system’s state space. .

  8. From Scorecard to Social Learning: A Reflective Coassessment Approach for Promoting Multiagency Cooperation in Natural Resource Management

    Directory of Open Access Journals (Sweden)

    Dirk J. Roux

    2011-03-01

    Full Text Available The responsibility for managing and conserving freshwater ecosystems is typically shared by multiple organizations with sometimes conflicting policy mandates. However, scorecard-based approaches for measuring management effectiveness in natural resource management are usually confined to single organizations. This paper describes a social learning approach which acknowledges cooperation as an essential precondition for effective management and that encourages reflective coassessment of cooperative relationships. The approach was pilot tested with eight participating organizations in one water management area in South Africa. It specifically aimed to allow for a multiagency reflective assessment of issues determining cooperative behavior, allow context-specific adaptations, and be embedded in adaptive management. It involved development of a spreadsheet-based scorecard-type tool that can be used to facilitate a multiagency workshop. This workshop serves to bring parties face-to-face and helps them codiscover their interdependence, shortcomings, and strengths. The spreadsheet structures reflection on their respective roles and effectiveness while the reflective coassessment motivates participants to address shortcomings. Overall, insights that emerged included: cooperation should be an explicit component of each organization's operational strategy; facilitation of appropriate cooperative behavior could be very effectively achieved by external "bridging organizations"; the reflective assessment process must be followed by purposefully adaptive interventions; the ability of the scorecard to be contextually adaptive was important; and institutional readiness requires investigation as the approach does sit somewhat uncomfortably with much current practice.

  9. Applications of Deep Learning and Reinforcement Learning to Biological Data.

    Science.gov (United States)

    Mahmud, Mufti; Kaiser, Mohammed Shamim; Hussain, Amir; Vassanelli, Stefano

    2018-06-01

    Rapid advances in hardware-based technologies during the past decades have opened up new possibilities for life scientists to gather multimodal data in various application domains, such as omics, bioimaging, medical imaging, and (brain/body)-machine interfaces. These have generated novel opportunities for development of dedicated data-intensive machine learning techniques. In particular, recent research in deep learning (DL), reinforcement learning (RL), and their combination (deep RL) promise to revolutionize the future of artificial intelligence. The growth in computational power accompanied by faster and increased data storage, and declining computing costs have already allowed scientists in various fields to apply these techniques on data sets that were previously intractable owing to their size and complexity. This paper provides a comprehensive survey on the application of DL, RL, and deep RL techniques in mining biological data. In addition, we compare the performances of DL techniques when applied to different data sets across various application domains. Finally, we outline open issues in this challenging research area and discuss future development perspectives.

  10. Social Learning, Reinforcement and Crime: Evidence from Three European Cities

    Science.gov (United States)

    Tittle, Charles R.; Antonaccio, Olena; Botchkovar, Ekaterina

    2012-01-01

    This study reports a cross-cultural test of Social Learning Theory using direct measures of social learning constructs and focusing on the causal structure implied by the theory. Overall, the results strongly confirm the main thrust of the theory. Prior criminal reinforcement and current crime-favorable definitions are highly related in all three…

  11. Systems control with generalized probabilistic fuzzy-reinforcement learning

    NARCIS (Netherlands)

    Hinojosa, J.; Nefti, S.; Kaymak, U.

    2011-01-01

    Reinforcement learning (RL) is a valuable learning method when the systems require a selection of control actions whose consequences emerge over long periods for which input-output data are not available. In most combinations of fuzzy systems and RL, the environment is considered to be

  12. Human-level control through deep reinforcement learning

    Science.gov (United States)

    Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Rusu, Andrei A.; Veness, Joel; Bellemare, Marc G.; Graves, Alex; Riedmiller, Martin; Fidjeland, Andreas K.; Ostrovski, Georg; Petersen, Stig; Beattie, Charles; Sadik, Amir; Antonoglou, Ioannis; King, Helen; Kumaran, Dharshan; Wierstra, Daan; Legg, Shane; Hassabis, Demis

    2015-02-01

    The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

  13. Human-level control through deep reinforcement learning.

    Science.gov (United States)

    Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Rusu, Andrei A; Veness, Joel; Bellemare, Marc G; Graves, Alex; Riedmiller, Martin; Fidjeland, Andreas K; Ostrovski, Georg; Petersen, Stig; Beattie, Charles; Sadik, Amir; Antonoglou, Ioannis; King, Helen; Kumaran, Dharshan; Wierstra, Daan; Legg, Shane; Hassabis, Demis

    2015-02-26

    The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

  14. A novel multi-agent decentralized win or learn fast policy hill-climbing with eligibility trace algorithm for smart generation control of interconnected complex power grids

    International Nuclear Information System (INIS)

    Xi, Lei; Yu, Tao; Yang, Bo; Zhang, Xiaoshun

    2015-01-01

    Highlights: • Proposing a decentralized smart generation control scheme for the automatic generation control coordination. • A novel multi-agent learning algorithm is developed to resolve stochastic control problems in power systems. • A variable learning rate are introduced base on the framework of stochastic games. • A simulation platform is developed to test the performance of different algorithms. - Abstract: This paper proposes a multi-agent smart generation control scheme for the automatic generation control coordination in interconnected complex power systems. A novel multi-agent decentralized win or learn fast policy hill-climbing with eligibility trace algorithm is developed, which can effectively identify the optimal average policies via a variable learning rate under various operation conditions. Based on control performance standards, the proposed approach is implemented in a flexible multi-agent stochastic dynamic game-based smart generation control simulation platform. Based on the mixed strategy and average policy, it is highly adaptive in stochastic non-Markov environments and large time-delay systems, which can fulfill automatic generation control coordination in interconnected complex power systems in the presence of increasing penetration of decentralized renewable energy. Two case studies on both a two-area load–frequency control power system and the China Southern Power Grid model have been done. Simulation results verify that multi-agent smart generation control scheme based on the proposed approach can obtain optimal average policies thus improve the closed-loop system performances, and can achieve a fast convergence rate with significant robustness compared with other methods

  15. Social Cognition as Reinforcement Learning: Feedback Modulates Emotion Inference.

    Science.gov (United States)

    Zaki, Jamil; Kallman, Seth; Wimmer, G Elliott; Ochsner, Kevin; Shohamy, Daphna

    2016-09-01

    Neuroscientific studies of social cognition typically employ paradigms in which perceivers draw single-shot inferences about the internal states of strangers. Real-world social inference features much different parameters: People often encounter and learn about particular social targets (e.g., friends) over time and receive feedback about whether their inferences are correct or incorrect. Here, we examined this process and, more broadly, the intersection between social cognition and reinforcement learning. Perceivers were scanned using fMRI while repeatedly encountering three social targets who produced conflicting visual and verbal emotional cues. Perceivers guessed how targets felt and received feedback about whether they had guessed correctly. Visual cues reliably predicted one target's emotion, verbal cues predicted a second target's emotion, and neither reliably predicted the third target's emotion. Perceivers successfully used this information to update their judgments over time. Furthermore, trial-by-trial learning signals-estimated using two reinforcement learning models-tracked activity in ventral striatum and ventromedial pFC, structures associated with reinforcement learning, and regions associated with updating social impressions, including TPJ. These data suggest that learning about others' emotions, like other forms of feedback learning, relies on domain-general reinforcement mechanisms as well as domain-specific social information processing.

  16. Can model-free reinforcement learning explain deontological moral judgments?

    Science.gov (United States)

    Ayars, Alisabeth

    2016-05-01

    Dual-systems frameworks propose that moral judgments are derived from both an immediate emotional response, and controlled/rational cognition. Recently Cushman (2013) proposed a new dual-system theory based on model-free and model-based reinforcement learning. Model-free learning attaches values to actions based on their history of reward and punishment, and explains some deontological, non-utilitarian judgments. Model-based learning involves the construction of a causal model of the world and allows for far-sighted planning; this form of learning fits well with utilitarian considerations that seek to maximize certain kinds of outcomes. I present three concerns regarding the use of model-free reinforcement learning to explain deontological moral judgment. First, many actions that humans find aversive from model-free learning are not judged to be morally wrong. Moral judgment must require something in addition to model-free learning. Second, there is a dearth of evidence for central predictions of the reinforcement account-e.g., that people with different reinforcement histories will, all else equal, make different moral judgments. Finally, to account for the effect of intention within the framework requires certain assumptions which lack support. These challenges are reasonable foci for future empirical/theoretical work on the model-free/model-based framework. Copyright © 2016 Elsevier B.V. All rights reserved.

  17. Time representation in reinforcement learning models of the basal ganglia

    Directory of Open Access Journals (Sweden)

    Samuel Joseph Gershman

    2014-01-01

    Full Text Available Reinforcement learning models have been influential in understanding many aspects of basal ganglia function, from reward prediction to action selection. Time plays an important role in these models, but there is still no theoretical consensus about what kind of time representation is used by the basal ganglia. We review several theoretical accounts and their supporting evidence. We then discuss the relationship between reinforcement learning models and the timing mechanisms that have been attributed to the basal ganglia. We hypothesize that a single computational system may underlie both reinforcement learning and interval timing—the perception of duration in the range of seconds to hours. This hypothesis, which extends earlier models by incorporating a time-sensitive action selection mechanism, may have important implications for understanding disorders like Parkinson's disease in which both decision making and timing are impaired.

  18. Adaptive Trajectory Tracking Control using Reinforcement Learning for Quadrotor

    Directory of Open Access Journals (Sweden)

    Wenjie Lou

    2016-02-01

    Full Text Available Inaccurate system parameters and unpredicted external disturbances affect the performance of non-linear controllers. In this paper, a new adaptive control algorithm under the reinforcement framework is proposed to stabilize a quadrotor helicopter. Based on a command-filtered non-linear control algorithm, adaptive elements are added and learned by policy-search methods. To predict the inaccurate system parameters, a new kernel-based regression learning method is provided. In addition, Policy learning by Weighting Exploration with the Returns (PoWER and Return Weighted Regression (RWR are utilized to learn the appropriate parameters for adaptive elements in order to cancel the effect of external disturbance. Furthermore, numerical simulations under several conditions are performed, and the ability of adaptive trajectory-tracking control with reinforcement learning are demonstrated.

  19. The Computational Development of Reinforcement Learning during Adolescence.

    Directory of Open Access Journals (Sweden)

    Stefano Palminteri

    2016-06-01

    Full Text Available Adolescence is a period of life characterised by changes in learning and decision-making. Learning and decision-making do not rely on a unitary system, but instead require the coordination of different cognitive processes that can be mathematically formalised as dissociable computational modules. Here, we aimed to trace the developmental time-course of the computational modules responsible for learning from reward or punishment, and learning from counterfactual feedback. Adolescents and adults carried out a novel reinforcement learning paradigm in which participants learned the association between cues and probabilistic outcomes, where the outcomes differed in valence (reward versus punishment and feedback was either partial or complete (either the outcome of the chosen option only, or the outcomes of both the chosen and unchosen option, were displayed. Computational strategies changed during development: whereas adolescents' behaviour was better explained by a basic reinforcement learning algorithm, adults' behaviour integrated increasingly complex computational features, namely a counterfactual learning module (enabling enhanced performance in the presence of complete feedback and a value contextualisation module (enabling symmetrical reward and punishment learning. Unlike adults, adolescent performance did not benefit from counterfactual (complete feedback. In addition, while adults learned symmetrically from both reward and punishment, adolescents learned from reward but were less likely to learn from punishment. This tendency to rely on rewards and not to consider alternative consequences of actions might contribute to our understanding of decision-making in adolescence.

  20. Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening

    OpenAIRE

    He, Frank S.; Liu, Yang; Schwing, Alexander G.; Peng, Jian

    2016-01-01

    We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique makes deep reinforcement learning more practical by drastically reducing the training time. We evaluate the performance of our approach on the 49 games of the challenging Arcade Learning Environment, and report significant improvements in both training time and...

  1. Reinforcement and inference in cross-situational word learning.

    Science.gov (United States)

    Tilles, Paulo F C; Fontanari, José F

    2013-01-01

    Cross-situational word learning is based on the notion that a learner can determine the referent of a word by finding something in common across many observed uses of that word. Here we propose an adaptive learning algorithm that contains a parameter that controls the strength of the reinforcement applied to associations between concurrent words and referents, and a parameter that regulates inference, which includes built-in biases, such as mutual exclusivity, and information of past learning events. By adjusting these parameters so that the model predictions agree with data from representative experiments on cross-situational word learning, we were able to explain the learning strategies adopted by the participants of those experiments in terms of a trade-off between reinforcement and inference. These strategies can vary wildly depending on the conditions of the experiments. For instance, for fast mapping experiments (i.e., the correct referent could, in principle, be inferred in a single observation) inference is prevalent, whereas for segregated contextual diversity experiments (i.e., the referents are separated in groups and are exhibited with members of their groups only) reinforcement is predominant. Other experiments are explained with more balanced doses of reinforcement and inference.

  2. Flow Navigation by Smart Microswimmers via Reinforcement Learning

    Science.gov (United States)

    Colabrese, Simona; Biferale, Luca; Celani, Antonio; Gustavsson, Kristian

    2017-11-01

    We have numerically modeled active particles which are able to acquire some limited knowledge of the fluid environment from simple mechanical cues and exert a control on their preferred steering direction. We show that those swimmers can learn effective strategies just by experience, using a reinforcement learning algorithm. As an example, we focus on smart gravitactic swimmers. These are active particles whose task is to reach the highest altitude within some time horizon, exploiting the underlying flow whenever possible. The reinforcement learning algorithm allows particles to learn effective strategies even in difficult situations when, in the absence of control, they would end up being trapped by flow structures. These strategies are highly nontrivial and cannot be easily guessed in advance. This work paves the way towards the engineering of smart microswimmers that solve difficult navigation problems. ERC AdG NewTURB 339032.

  3. Reinforcement and Systemic Machine Learning for Decision Making

    CERN Document Server

    Kulkarni, Parag

    2012-01-01

    Reinforcement and Systemic Machine Learning for Decision Making There are always difficulties in making machines that learn from experience. Complete information is not always available-or it becomes available in bits and pieces over a period of time. With respect to systemic learning, there is a need to understand the impact of decisions and actions on a system over that period of time. This book takes a holistic approach to addressing that need and presents a new paradigm-creating new learning applications and, ultimately, more intelligent machines. The first book of its kind in this new an

  4. Reinforcement Learning for Online Control of Evolutionary Algorithms

    NARCIS (Netherlands)

    Eiben, A.; Horvath, Mark; Kowalczyk, Wojtek; Schut, Martijn

    2007-01-01

    The research reported in this paper is concerned with assessing the usefulness of reinforcment learning (RL) for on-line calibration of parameters in evolutionary algorithms (EA). We are running an RL procedure and the EA simultaneously and the RL is changing the EA parameters on-the-fly. We

  5. Emotion in reinforcement learning agents and robots : A survey

    NARCIS (Netherlands)

    Moerland, T.M.; Broekens, D.J.; Jonker, C.M.

    2018-01-01

    This article provides the first survey of computational models of emotion in reinforcement learning (RL) agents. The survey focuses on agent/robot emotions, and mostly ignores human user emotions. Emotions are recognized as functional in decision-making by influencing motivation and action

  6. Perceptual learning rules based on reinforcers and attention

    NARCIS (Netherlands)

    Roelfsema, Pieter R.; van Ooyen, Arjen; Watanabe, Takeo

    2010-01-01

    How does the brain learn those visual features that are relevant for behavior? In this article, we focus on two factors that guide plasticity of visual representations. First, reinforcers cause the global release of diffusive neuromodulatory signals that gate plasticity. Second, attentional feedback

  7. Optimal Control via Reinforcement Learning with Symbolic Policy Approximation

    NARCIS (Netherlands)

    Kubalìk, Jiřì; Alibekov, Eduard; Babuska, R.; Dochain, Denis; Henrion, Didier; Peaucelle, Dimitri

    2017-01-01

    Model-based reinforcement learning (RL) algorithms can be used to derive optimal control laws for nonlinear dynamic systems. With continuous-valued state and input variables, RL algorithms have to rely on function approximators to represent the value function and policy mappings. This paper

  8. Joy, Distress, Hope, and Fear in Reinforcement Learning (Extended Abstract)

    NARCIS (Netherlands)

    Jacobs, E.J.; Broekens, J.; Jonker, C.M.

    2014-01-01

    In this paper we present a mapping between joy, distress, hope and fear, and Reinforcement Learning primitives. Joy / distress is a signal that is derived from the RL update signal, while hope/fear is derived from the utility of the current state. Agent-based simulation experiments replicate

  9. Reinforcement Learning Explains Conditional Cooperation and Its Moody Cousin.

    Directory of Open Access Journals (Sweden)

    Takahiro Ezaki

    2016-07-01

    Full Text Available Direct reciprocity, or repeated interaction, is a main mechanism to sustain cooperation under social dilemmas involving two individuals. For larger groups and networks, which are probably more relevant to understanding and engineering our society, experiments employing repeated multiplayer social dilemma games have suggested that humans often show conditional cooperation behavior and its moody variant. Mechanisms underlying these behaviors largely remain unclear. Here we provide a proximate account for this behavior by showing that individuals adopting a type of reinforcement learning, called aspiration learning, phenomenologically behave as conditional cooperator. By definition, individuals are satisfied if and only if the obtained payoff is larger than a fixed aspiration level. They reinforce actions that have resulted in satisfactory outcomes and anti-reinforce those yielding unsatisfactory outcomes. The results obtained in the present study are general in that they explain extant experimental results obtained for both so-called moody and non-moody conditional cooperation, prisoner's dilemma and public goods games, and well-mixed groups and networks. Different from the previous theory, individuals are assumed to have no access to information about what other individuals are doing such that they cannot explicitly use conditional cooperation rules. In this sense, myopic aspiration learning in which the unconditional propensity of cooperation is modulated in every discrete time step explains conditional behavior of humans. Aspiration learners showing (moody conditional cooperation obeyed a noisy GRIM-like strategy. This is different from the Pavlov, a reinforcement learning strategy promoting mutual cooperation in two-player situations.

  10. Collaborative multi-agent reinforcement learning based on a novel coordination tree frame with dynamic partition

    NARCIS (Netherlands)

    Fang, M.; Groen, F.C.A.; Li, H.; Zhang, J.

    2014-01-01

    In the research of team Markov games, computing the coordinate team dynamically and determining the joint action policy are the main problems. To deal with the first problem, a dynamic team partitioning method is proposed based on a novel coordinate tree frame. We build a coordinate tree with

  11. Neurofeedback in Learning Disabled Children: Visual versus Auditory Reinforcement.

    Science.gov (United States)

    Fernández, Thalía; Bosch-Bayard, Jorge; Harmony, Thalía; Caballero, María I; Díaz-Comas, Lourdes; Galán, Lídice; Ricardo-Garcell, Josefina; Aubert, Eduardo; Otero-Ojeda, Gloria

    2016-03-01

    Children with learning disabilities (LD) frequently have an EEG characterized by an excess of theta and a deficit of alpha activities. NFB using an auditory stimulus as reinforcer has proven to be a useful tool to treat LD children by positively reinforcing decreases of the theta/alpha ratio. The aim of the present study was to optimize the NFB procedure by comparing the efficacy of visual (with eyes open) versus auditory (with eyes closed) reinforcers. Twenty LD children with an abnormally high theta/alpha ratio were randomly assigned to the Auditory or the Visual group, where a 500 Hz tone or a visual stimulus (a white square), respectively, was used as a positive reinforcer when the value of the theta/alpha ratio was reduced. Both groups had signs consistent with EEG maturation, but only the Auditory Group showed behavioral/cognitive improvements. In conclusion, the auditory reinforcer was more efficacious in reducing the theta/alpha ratio, and it improved the cognitive abilities more than the visual reinforcer.

  12. Study and Application of Reinforcement Learning in Cooperative Strategy of the Robot Soccer Based on BDI Model

    Directory of Open Access Journals (Sweden)

    Wu Bo-ying

    2009-11-01

    Full Text Available The dynamic cooperation model of multi-Agent is formed by combining reinforcement learning with BDI model. In this model, the concept of the individual optimization loses its meaning, because the repayment of each Agent dose not only depend on itsself but also on the choice of other Agents. All Agents can pursue a common optimum solution and try to realize the united intention as a whole to a maximum limit. The robot moves to its goal, depending on the present positions of the other robots that cooperate with it and the present position of the ball. One of these robots cooperating with it is controlled to move by man with a joystick. In this way, Agent can be ensured to search for each state-action as frequently as possible when it carries on choosing movements, so as to shorten the time of searching for the movement space so that the convergence speed of reinforcement learning can be improved. The validity of the proposed cooperative strategy for the robot soccer has been proved by combining theoretical analysis with simulation robot soccer match (11vs11 .

  13. Structure identification in fuzzy inference using reinforcement learning

    Science.gov (United States)

    Berenji, Hamid R.; Khedkar, Pratap

    1993-01-01

    In our previous work on the GARIC architecture, we have shown that the system can start with surface structure of the knowledge base (i.e., the linguistic expression of the rules) and learn the deep structure (i.e., the fuzzy membership functions of the labels used in the rules) by using reinforcement learning. Assuming the surface structure, GARIC refines the fuzzy membership functions used in the consequents of the rules using a gradient descent procedure. This hybrid fuzzy logic and reinforcement learning approach can learn to balance a cart-pole system and to backup a truck to its docking location after a few trials. In this paper, we discuss how to do structure identification using reinforcement learning in fuzzy inference systems. This involves identifying both surface as well as deep structure of the knowledge base. The term set of fuzzy linguistic labels used in describing the values of each control variable must be derived. In this process, splitting a label refers to creating new labels which are more granular than the original label and merging two labels creates a more general label. Splitting and merging of labels directly transform the structure of the action selection network used in GARIC by increasing or decreasing the number of hidden layer nodes.

  14. A multiplicative reinforcement learning model capturing learning dynamics and interindividual variability in mice

    OpenAIRE

    Bathellier, Brice; Tee, Sui Poh; Hrovat, Christina; Rumpel, Simon

    2013-01-01

    Learning speed can strongly differ across individuals. This is seen in humans and animals. Here, we measured learning speed in mice performing a discrimination task and developed a theoretical model based on the reinforcement learning framework to account for differences between individual mice. We found that, when using a multiplicative learning rule, the starting connectivity values of the model strongly determine the shape of learning curves. This is in contrast to current learning models ...

  15. Distributed Economic Dispatch in Microgrids Based on Cooperative Reinforcement Learning.

    Science.gov (United States)

    Liu, Weirong; Zhuang, Peng; Liang, Hao; Peng, Jun; Huang, Zhiwu; Weirong Liu; Peng Zhuang; Hao Liang; Jun Peng; Zhiwu Huang; Liu, Weirong; Liang, Hao; Peng, Jun; Zhuang, Peng; Huang, Zhiwu

    2018-06-01

    Microgrids incorporated with distributed generation (DG) units and energy storage (ES) devices are expected to play more and more important roles in the future power systems. Yet, achieving efficient distributed economic dispatch in microgrids is a challenging issue due to the randomness and nonlinear characteristics of DG units and loads. This paper proposes a cooperative reinforcement learning algorithm for distributed economic dispatch in microgrids. Utilizing the learning algorithm can avoid the difficulty of stochastic modeling and high computational complexity. In the cooperative reinforcement learning algorithm, the function approximation is leveraged to deal with the large and continuous state spaces. And a diffusion strategy is incorporated to coordinate the actions of DG units and ES devices. Based on the proposed algorithm, each node in microgrids only needs to communicate with its local neighbors, without relying on any centralized controllers. Algorithm convergence is analyzed, and simulations based on real-world meteorological and load data are conducted to validate the performance of the proposed algorithm.

  16. Challenges in the Verification of Reinforcement Learning Algorithms

    Science.gov (United States)

    Van Wesel, Perry; Goodloe, Alwyn E.

    2017-01-01

    Machine learning (ML) is increasingly being applied to a wide array of domains from search engines to autonomous vehicles. These algorithms, however, are notoriously complex and hard to verify. This work looks at the assumptions underlying machine learning algorithms as well as some of the challenges in trying to verify ML algorithms. Furthermore, we focus on the specific challenges of verifying reinforcement learning algorithms. These are highlighted using a specific example. Ultimately, we do not offer a solution to the complex problem of ML verification, but point out possible approaches for verification and interesting research opportunities.

  17. Amygdala and ventral striatum make distinct contributions to reinforcement learning

    Science.gov (United States)

    Costa, Vincent D.; Monte, Olga Dal; Lucas, Daniel R.; Murray, Elisabeth A.; Averbeck, Bruno B.

    2016-01-01

    Summary Reinforcement learning (RL) theories posit that dopaminergic signals are integrated within the striatum to associate choices with outcomes. Often overlooked is that the amygdala also receives dopaminergic input and is involved in Pavlovian processes that influence choice behavior. To determine the relative contributions of the ventral striatum (VS) and amygdala to appetitive RL we tested rhesus macaques with VS or amygdala lesions on deterministic and stochastic versions of a two-arm bandit reversal learning task. When learning was characterized with a RL model relative to controls, amygdala lesions caused general decreases in learning from positive feedback and choice consistency. By comparison, VS lesions only affected learning in the stochastic task. Moreover, the VS lesions hastened the monkeys’ choice reaction times, which emphasized a speed-accuracy tradeoff that accounted for errors in deterministic learning. These results update standard accounts of RL by emphasizing distinct contributions of the amygdala and VS to RL. PMID:27720488

  18. A Neuro-Control Design Based on Fuzzy Reinforcement Learning

    DEFF Research Database (Denmark)

    Katebi, S.D.; Blanke, M.

    This paper describes a neuro-control fuzzy critic design procedure based on reinforcement learning. An important component of the proposed intelligent control configuration is the fuzzy credit assignment unit which acts as a critic, and through fuzzy implications provides adjustment mechanisms....... The fuzzy credit assignment unit comprises a fuzzy system with the appropriate fuzzification, knowledge base and defuzzification components. When an external reinforcement signal (a failure signal) is received, sequences of control actions are evaluated and modified by the action applier unit. The desirable...... ones instruct the neuro-control unit to adjust its weights and are simultaneously stored in the memory unit during the training phase. In response to the internal reinforcement signal (set point threshold deviation), the stored information is retrieved by the action applier unit and utilized for re...

  19. Projective Simulation compared to reinforcement learning

    OpenAIRE

    Bjerland, Øystein Førsund

    2015-01-01

    This thesis explores the model of projective simulation (PS), a novel approach for an artificial intelligence (AI) agent. The model of PS learns by interacting with the environment it is situated in, and allows for simulating actions before real action is taken. The action selection is based on a random walk through the episodic & compositional memory (ECM), which is a network of clips that represent previous experienced percepts. The network takes percepts as inpu...

  20. Reinforcement Learning Applications to Combat Identification

    Science.gov (United States)

    2017-03-01

    ruleset in an effort to mimic simplistic cognitive decision making of a TAO/MC and establishes parameters for the experimentation. Also, there is an...the process knowledge and decision - making abilities of the human decision maker. “[A] cognitive architecture provides the fixed processes and...have bearing on decisions to affect the learning rate in an operational implementation. 3. Cognitive Functions in CID The translation of the

  1. Reinforcement learning for optimal control of low exergy buildings

    International Nuclear Information System (INIS)

    Yang, Lei; Nagy, Zoltan; Goffin, Philippe; Schlueter, Arno

    2015-01-01

    Highlights: • Implementation of reinforcement learning control for LowEx Building systems. • Learning allows adaptation to local environment without prior knowledge. • Presentation of reinforcement learning control for real-life applications. • Discussion of the applicability for real-life situations. - Abstract: Over a third of the anthropogenic greenhouse gas (GHG) emissions stem from cooling and heating buildings, due to their fossil fuel based operation. Low exergy building systems are a promising approach to reduce energy consumption as well as GHG emissions. They consists of renewable energy technologies, such as PV, PV/T and heat pumps. Since careful tuning of parameters is required, a manual setup may result in sub-optimal operation. A model predictive control approach is unnecessarily complex due to the required model identification. Therefore, in this work we present a reinforcement learning control (RLC) approach. The studied building consists of a PV/T array for solar heat and electricity generation, as well as geothermal heat pumps. We present RLC for the PV/T array, and the full building model. Two methods, Tabular Q-learning and Batch Q-learning with Memory Replay, are implemented with real building settings and actual weather conditions in a Matlab/Simulink framework. The performance is evaluated against standard rule-based control (RBC). We investigated different neural network structures and find that some outperformed RBC already during the learning phase. Overall, every RLC strategy for PV/T outperformed RBC by over 10% after the third year. Likewise, for the full building, RLC outperforms RBC in terms of meeting the heating demand, maintaining the optimal operation temperature and compensating more effectively for ground heat. This allows to reduce engineering costs associated with the setup of these systems, as well as decrease the return-of-invest period, both of which are necessary to create a sustainable, zero-emission building

  2. Pleasurable music affects reinforcement learning according to the listener

    Science.gov (United States)

    Gold, Benjamin P.; Frank, Michael J.; Bogert, Brigitte; Brattico, Elvira

    2013-01-01

    Mounting evidence links the enjoyment of music to brain areas implicated in emotion and the dopaminergic reward system. In particular, dopamine release in the ventral striatum seems to play a major role in the rewarding aspect of music listening. Striatal dopamine also influences reinforcement learning, such that subjects with greater dopamine efficacy learn better to approach rewards while those with lesser dopamine efficacy learn better to avoid punishments. In this study, we explored the practical implications of musical pleasure through its ability to facilitate reinforcement learning via non-pharmacological dopamine elicitation. Subjects from a wide variety of musical backgrounds chose a pleasurable and a neutral piece of music from an experimenter-compiled database, and then listened to one or both of these pieces (according to pseudo-random group assignment) as they performed a reinforcement learning task dependent on dopamine transmission. We assessed musical backgrounds as well as typical listening patterns with the new Helsinki Inventory of Music and Affective Behaviors (HIMAB), and separately investigated behavior for the training and test phases of the learning task. Subjects with more musical experience trained better with neutral music and tested better with pleasurable music, while those with less musical experience exhibited the opposite effect. HIMAB results regarding listening behaviors and subjective music ratings indicate that these effects arose from different listening styles: namely, more affective listening in non-musicians and more analytical listening in musicians. In conclusion, musical pleasure was able to influence task performance, and the shape of this effect depended on group and individual factors. These findings have implications in affective neuroscience, neuroaesthetics, learning, and music therapy. PMID:23970875

  3. Simulation-based optimization parametric optimization techniques and reinforcement learning

    CERN Document Server

    Gosavi, Abhijit

    2003-01-01

    Simulation-Based Optimization: Parametric Optimization Techniques and Reinforcement Learning introduces the evolving area of simulation-based optimization. The book's objective is two-fold: (1) It examines the mathematical governing principles of simulation-based optimization, thereby providing the reader with the ability to model relevant real-life problems using these techniques. (2) It outlines the computational technology underlying these methods. Taken together these two aspects demonstrate that the mathematical and computational methods discussed in this book do work. Broadly speaking, the book has two parts: (1) parametric (static) optimization and (2) control (dynamic) optimization. Some of the book's special features are: *An accessible introduction to reinforcement learning and parametric-optimization techniques. *A step-by-step description of several algorithms of simulation-based optimization. *A clear and simple introduction to the methodology of neural networks. *A gentle introduction to converg...

  4. Reinforcement active learning in the vibrissae system: optimal object localization.

    Science.gov (United States)

    Gordon, Goren; Dorfman, Nimrod; Ahissar, Ehud

    2013-01-01

    Rats move their whiskers to acquire information about their environment. It has been observed that they palpate novel objects and objects they are required to localize in space. We analyze whisker-based object localization using two complementary paradigms, namely, active learning and intrinsic-reward reinforcement learning. Active learning algorithms select the next training samples according to the hypothesized solution in order to better discriminate between correct and incorrect labels. Intrinsic-reward reinforcement learning uses prediction errors as the reward to an actor-critic design, such that behavior converges to the one that optimizes the learning process. We show that in the context of object localization, the two paradigms result in palpation whisking as their respective optimal solution. These results suggest that rats may employ principles of active learning and/or intrinsic reward in tactile exploration and can guide future research to seek the underlying neuronal mechanisms that implement them. Furthermore, these paradigms are easily transferable to biomimetic whisker-based artificial sensors and can improve the active exploration of their environment. Copyright © 2012 Elsevier Ltd. All rights reserved.

  5. Human reinforcement learning subdivides structured action spaces by learning effector-specific values

    OpenAIRE

    Gershman, Samuel J.; Pesaran, Bijan; Daw, Nathaniel D.

    2009-01-01

    Humans and animals are endowed with a large number of effectors. Although this enables great behavioral flexibility, it presents an equally formidable reinforcement learning problem of discovering which actions are most valuable, due to the high dimensionality of the action space. An unresolved question is how neural systems for reinforcement learning – such as prediction error signals for action valuation associated with dopamine and the striatum – can cope with this “curse of dimensionality...

  6. Reinforcement learning produces dominant strategies for the Iterated Prisoner's Dilemma.

    Directory of Open Access Journals (Sweden)

    Marc Harper

    Full Text Available We present tournament results and several powerful strategies for the Iterated Prisoner's Dilemma created using reinforcement learning techniques (evolutionary and particle swarm algorithms. These strategies are trained to perform well against a corpus of over 170 distinct opponents, including many well-known and classic strategies. All the trained strategies win standard tournaments against the total collection of other opponents. The trained strategies and one particular human made designed strategy are the top performers in noisy tournaments also.

  7. Intranasal oxytocin enhances socially-reinforced learning in rhesus monkeys

    Directory of Open Access Journals (Sweden)

    Lisa A Parr

    2014-09-01

    Full Text Available There are currently no drugs approved for the treatment of social deficits associated with autism spectrum disorders (ASD. One hypothesis for these deficits is that individuals with ASD lack the motivation to attend to social cues because those cues are not implicitly rewarding. Therefore, any drug that could enhance the rewarding quality of social stimuli could have a profound impact on the treatment of ASD, and other social disorders. Oxytocin (OT is a neuropeptide that has been effective in enhancing social cognition and social reward in humans. The present study examined the ability of OT to selectively enhance learning after social compared to nonsocial reward in rhesus monkeys, an important species for modeling the neurobiology of social behavior in humans. Monkeys were required to learn an implicit visual matching task after receiving either intranasal (IN OT or Placebo (saline. Correct trials were rewarded with the presentation of positive and negative social (play faces/threat faces or nonsocial (banana/cage locks stimuli, plus food. Incorrect trials were not rewarded. Results demonstrated a strong effect of socially-reinforced learning, monkeys’ performed significantly better when reinforced with social versus nonsocial stimuli. Additionally, socially-reinforced learning was significantly better and occurred faster after IN-OT compared to placebo treatment. Performance in the IN-OT, but not Placebo, condition was also significantly better when the reinforcement stimuli were emotionally positive compared to negative facial expressions. These data support the hypothesis that OT may function to enhance prosocial behavior in primates by increasing the rewarding quality of emotionally positive, social compared to emotionally negative or nonsocial images. These data also support the use of the rhesus monkey as a model for exploring the neurobiological basis of social behavior and its impairment.

  8. Reinforcement learning produces dominant strategies for the Iterated Prisoner's Dilemma.

    Science.gov (United States)

    Harper, Marc; Knight, Vincent; Jones, Martin; Koutsovoulos, Georgios; Glynatsi, Nikoleta E; Campbell, Owen

    2017-01-01

    We present tournament results and several powerful strategies for the Iterated Prisoner's Dilemma created using reinforcement learning techniques (evolutionary and particle swarm algorithms). These strategies are trained to perform well against a corpus of over 170 distinct opponents, including many well-known and classic strategies. All the trained strategies win standard tournaments against the total collection of other opponents. The trained strategies and one particular human made designed strategy are the top performers in noisy tournaments also.

  9. Emotion in reinforcement learning agents and robots: A survey

    OpenAIRE

    Moerland, T.M.; Broekens, D.J.; Jonker, C.M.

    2018-01-01

    This article provides the first survey of computational models of emotion in reinforcement learning (RL) agents. The survey focuses on agent/robot emotions, and mostly ignores human user emotions. Emotions are recognized as functional in decision-making by influencing motivation and action selection. Therefore, computational emotion models are usually grounded in the agent's decision making architecture, of which RL is an important subclass. Studying emotions in RL-based agents is useful for ...

  10. Modeling Avoidance in Mood and Anxiety Disorders Using Reinforcement Learning.

    Science.gov (United States)

    Mkrtchian, Anahit; Aylward, Jessica; Dayan, Peter; Roiser, Jonathan P; Robinson, Oliver J

    2017-10-01

    Serious and debilitating symptoms of anxiety are the most common mental health problem worldwide, accounting for around 5% of all adult years lived with disability in the developed world. Avoidance behavior-avoiding social situations for fear of embarrassment, for instance-is a core feature of such anxiety. However, as for many other psychiatric symptoms the biological mechanisms underlying avoidance remain unclear. Reinforcement learning models provide formal and testable characterizations of the mechanisms of decision making; here, we examine avoidance in these terms. A total of 101 healthy participants and individuals with mood and anxiety disorders completed an approach-avoidance go/no-go task under stress induced by threat of unpredictable shock. We show an increased reliance in the mood and anxiety group on a parameter of our reinforcement learning model that characterizes a prepotent (pavlovian) bias to withhold responding in the face of negative outcomes. This was particularly the case when the mood and anxiety group was under stress. This formal description of avoidance within the reinforcement learning framework provides a new means of linking clinical symptoms with biophysically plausible models of neural circuitry and, as such, takes us closer to a mechanistic understanding of mood and anxiety disorders. Copyright © 2017 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.

  11. Towards autonomous neuroprosthetic control using Hebbian reinforcement learning.

    Science.gov (United States)

    Mahmoudi, Babak; Pohlmeyer, Eric A; Prins, Noeline W; Geng, Shijia; Sanchez, Justin C

    2013-12-01

    Our goal was to design an adaptive neuroprosthetic controller that could learn the mapping from neural states to prosthetic actions and automatically adjust adaptation using only a binary evaluative feedback as a measure of desirability/undesirability of performance. Hebbian reinforcement learning (HRL) in a connectionist network was used for the design of the adaptive controller. The method combines the efficiency of supervised learning with the generality of reinforcement learning. The convergence properties of this approach were studied using both closed-loop control simulations and open-loop simulations that used primate neural data from robot-assisted reaching tasks. The HRL controller was able to perform classification and regression tasks using its episodic and sequential learning modes, respectively. In our experiments, the HRL controller quickly achieved convergence to an effective control policy, followed by robust performance. The controller also automatically stopped adapting the parameters after converging to a satisfactory control policy. Additionally, when the input neural vector was reorganized, the controller resumed adaptation to maintain performance. By estimating an evaluative feedback directly from the user, the HRL control algorithm may provide an efficient method for autonomous adaptation of neuroprosthetic systems. This method may enable the user to teach the controller the desired behavior using only a simple feedback signal.

  12. Functional Contour-following via Haptic Perception and Reinforcement Learning.

    Science.gov (United States)

    Hellman, Randall B; Tekin, Cem; van der Schaar, Mihaela; Santos, Veronica J

    2018-01-01

    Many tasks involve the fine manipulation of objects despite limited visual feedback. In such scenarios, tactile and proprioceptive feedback can be leveraged for task completion. We present an approach for real-time haptic perception and decision-making for a haptics-driven, functional contour-following task: the closure of a ziplock bag. This task is challenging for robots because the bag is deformable, transparent, and visually occluded by artificial fingertip sensors that are also compliant. A deep neural net classifier was trained to estimate the state of a zipper within a robot's pinch grasp. A Contextual Multi-Armed Bandit (C-MAB) reinforcement learning algorithm was implemented to maximize cumulative rewards by balancing exploration versus exploitation of the state-action space. The C-MAB learner outperformed a benchmark Q-learner by more efficiently exploring the state-action space while learning a hard-to-code task. The learned C-MAB policy was tested with novel ziplock bag scenarios and contours (wire, rope). Importantly, this work contributes to the development of reinforcement learning approaches that account for limited resources such as hardware life and researcher time. As robots are used to perform complex, physically interactive tasks in unstructured or unmodeled environments, it becomes important to develop methods that enable efficient and effective learning with physical testbeds.

  13. An adaptive multi-agent memetic system for personalizing e-learning experiences

    NARCIS (Netherlands)

    Acampora, G.; Gaeta, M.; Munoz, E.; Vitiello, A.

    2011-01-01

    The rapid changes in modern knowledge, due to exponential growth of information sources, are complicating learners' activity. For this reason, novel approaches are necessary to obtain suitable learning solutions able to generate efficient, personalized and flexible learning experiences. From this

  14. Learning from induced changes in opponent (re)actions in multi-agent games

    NARCIS (Netherlands)

    P.J. 't Hoen (Pieter Jan); S.M. Bohte (Sander); J.A. La Poutré (Han)

    2005-01-01

    textabstractMulti-agent learning is a growing area of research. An important topic is to formulate how an agent can learn a good policy in the face of adaptive, competitive opponents. Most research has focused on extensions of single agent learning techniques originally designed for agents in more

  15. Proposed Methodology for Application of Human-like gradual Multi-Agent Q-Learning (HuMAQ) for Multi-robot Exploration

    International Nuclear Information System (INIS)

    Ray, Dip Narayan; Majumder, Somajyoti

    2014-01-01

    Several attempts have been made by the researchers around the world to develop a number of autonomous exploration techniques for robots. But it has been always an important issue for developing the algorithm for unstructured and unknown environments. Human-like gradual Multi-agent Q-leaming (HuMAQ) is a technique developed for autonomous robotic exploration in unknown (and even unimaginable) environments. It has been successfully implemented in multi-agent single robotic system. HuMAQ uses the concept of Subsumption architecture, a well-known Behaviour-based architecture for prioritizing the agents of the multi-agent system and executes only the most common action out of all the different actions recommended by different agents. Instead of using new state-action table (Q-table) each time, HuMAQ uses the immediate past table for efficient and faster exploration. The proof of learning has also been established both theoretically and practically. HuMAQ has the potential to be used in different and difficult situations as well as applications. The same architecture has been modified to use for multi-robot exploration in an environment. Apart from all other existing agents used in the single robotic system, agents for inter-robot communication and coordination/ co-operation with the other similar robots have been introduced in the present research. Current work uses a series of indigenously developed identical autonomous robotic systems, communicating with each other through ZigBee protocol

  16. Reinforcement Learning in the Game of Othello: Learning Against a Fixed Opponent and Learning from Self-Play

    NARCIS (Netherlands)

    van der Ree, Michiel; Wiering, Marco

    2013-01-01

    This paper compares three strategies in using reinforcement learning algorithms to let an artificial agent learnto play the game of Othello. The three strategies that are compared are: Learning by self-play, learning from playing against a fixed opponent, and learning from playing against a fixed

  17. Learning alternative movement coordination patterns using reinforcement feedback.

    Science.gov (United States)

    Lin, Tzu-Hsiang; Denomme, Amber; Ranganathan, Rajiv

    2018-05-01

    One of the characteristic features of the human motor system is redundancy-i.e., the ability to achieve a given task outcome using multiple coordination patterns. However, once participants settle on using a specific coordination pattern, the process of learning to use a new alternative coordination pattern to perform the same task is still poorly understood. Here, using two experiments, we examined this process of how participants shift from one coordination pattern to another using different reinforcement schedules. Participants performed a virtual reaching task, where they moved a cursor to different targets positioned on the screen. Our goal was to make participants use a coordination pattern with greater trunk motion, and to this end, we provided reinforcement by making the cursor disappear if the trunk motion during the reach did not cross a specified threshold value. In Experiment 1, we compared two reinforcement schedules in two groups of participants-an abrupt group, where the threshold was introduced immediately at the beginning of practice; and a gradual group, where the threshold was introduced gradually with practice. Results showed that both abrupt and gradual groups were effective in shifting their coordination patterns to involve greater trunk motion, but the abrupt group showed greater retention when the reinforcement was removed. In Experiment 2, we examined the basis of this advantage in the abrupt group using two additional control groups. Results showed that the advantage of the abrupt group was because of a greater number of practice trials with the desired coordination pattern. Overall, these results show that reinforcement can be successfully used to shift coordination patterns, which has potential in the rehabilitation of movement disorders.

  18. Manufacturing Scheduling Using Colored Petri Nets and Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Maria Drakaki

    2017-02-01

    Full Text Available Agent-based intelligent manufacturing control systems are capable to efficiently respond and adapt to environmental changes. Manufacturing system adaptation and evolution can be addressed with learning mechanisms that increase the intelligence of agents. In this paper a manufacturing scheduling method is presented based on Timed Colored Petri Nets (CTPNs and reinforcement learning (RL. CTPNs model the manufacturing system and implement the scheduling. In the search for an optimal solution a scheduling agent uses RL and in particular the Q-learning algorithm. A warehouse order-picking scheduling is presented as a case study to illustrate the method. The proposed scheduling method is compared to existing methods. Simulation and state space results are used to evaluate performance and identify system properties.

  19. Reinforcement Learning Based on the Bayesian Theorem for Electricity Markets Decision Support

    DEFF Research Database (Denmark)

    Sousa, Tiago; Pinto, Tiago; Praca, Isabel

    2014-01-01

    This paper presents the applicability of a reinforcement learning algorithm based on the application of the Bayesian theorem of probability. The proposed reinforcement learning algorithm is an advantageous and indispensable tool for ALBidS (Adaptive Learning strategic Bidding System), a multi...

  20. Reinforcement Learning Based Web Service Compositions for Mobile Business

    Science.gov (United States)

    Zhou, Juan; Chen, Shouming

    In this paper, we propose a new solution to Reactive Web Service Composition, via molding with Reinforcement Learning, and introducing modified (alterable) QoS variables into the model as elements in the Markov Decision Process tuple. Moreover, we give an example of Reactive-WSC-based mobile banking, to demonstrate the intrinsic capability of the solution in question of obtaining the optimized service composition, characterized by (alterable) target QoS variable sets with optimized values. Consequently, we come to the conclusion that the solution has decent potentials in boosting customer experiences and qualities of services in Web Services, and those in applications in the whole electronic commerce and business sector.

  1. Space Objects Maneuvering Detection and Prediction via Inverse Reinforcement Learning

    Science.gov (United States)

    Linares, R.; Furfaro, R.

    This paper determines the behavior of Space Objects (SOs) using inverse Reinforcement Learning (RL) to estimate the reward function that each SO is using for control. The approach discussed in this work can be used to analyze maneuvering of SOs from observational data. The inverse RL problem is solved using the Feature Matching approach. This approach determines the optimal reward function that a SO is using while maneuvering by assuming that the observed trajectories are optimal with respect to the SO's own reward function. This paper uses estimated orbital elements data to determine the behavior of SOs in a data-driven fashion.

  2. Finding intrinsic rewards by embodied evolution and constrained reinforcement learning.

    Science.gov (United States)

    Uchibe, Eiji; Doya, Kenji

    2008-12-01

    Understanding the design principle of reward functions is a substantial challenge both in artificial intelligence and neuroscience. Successful acquisition of a task usually requires not only rewards for goals, but also for intermediate states to promote effective exploration. This paper proposes a method for designing 'intrinsic' rewards of autonomous agents by combining constrained policy gradient reinforcement learning and embodied evolution. To validate the method, we use Cyber Rodent robots, in which collision avoidance, recharging from battery packs, and 'mating' by software reproduction are three major 'extrinsic' rewards. We show in hardware experiments that the robots can find appropriate 'intrinsic' rewards for the vision of battery packs and other robots to promote approach behaviors.

  3. Stochastic abstract policies: generalizing knowledge to improve reinforcement learning.

    Science.gov (United States)

    Koga, Marcelo L; Freire, Valdinei; Costa, Anna H R

    2015-01-01

    Reinforcement learning (RL) enables an agent to learn behavior by acquiring experience through trial-and-error interactions with a dynamic environment. However, knowledge is usually built from scratch and learning to behave may take a long time. Here, we improve the learning performance by leveraging prior knowledge; that is, the learner shows proper behavior from the beginning of a target task, using the knowledge from a set of known, previously solved, source tasks. In this paper, we argue that building stochastic abstract policies that generalize over past experiences is an effective way to provide such improvement and this generalization outperforms the current practice of using a library of policies. We achieve that contributing with a new algorithm, AbsProb-PI-multiple and a framework for transferring knowledge represented as a stochastic abstract policy in new RL tasks. Stochastic abstract policies offer an effective way to encode knowledge because the abstraction they provide not only generalizes solutions but also facilitates extracting the similarities among tasks. We perform experiments in a robotic navigation environment and analyze the agent's behavior throughout the learning process and also assess the transfer ratio for different amounts of source tasks. We compare our method with the transfer of a library of policies, and experiments show that the use of a generalized policy produces better results by more effectively guiding the agent when learning a target task.

  4. Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing

    OpenAIRE

    Le, Minh; Fokkens, Antske

    2017-01-01

    Error propagation is a common problem in NLP. Reinforcement learning explores erroneous states during training and can therefore be more robust when mistakes are made early in a process. In this paper, we apply reinforcement learning to greedy dependency parsing which is known to suffer from error propagation. Reinforcement learning improves accuracy of both labeled and unlabeled dependencies of the Stanford Neural Dependency Parser, a high performance greedy parser, while maintaining its eff...

  5. Human reinforcement learning subdivides structured action spaces by learning effector-specific values.

    Science.gov (United States)

    Gershman, Samuel J; Pesaran, Bijan; Daw, Nathaniel D

    2009-10-28

    Humans and animals are endowed with a large number of effectors. Although this enables great behavioral flexibility, it presents an equally formidable reinforcement learning problem of discovering which actions are most valuable because of the high dimensionality of the action space. An unresolved question is how neural systems for reinforcement learning-such as prediction error signals for action valuation associated with dopamine and the striatum-can cope with this "curse of dimensionality." We propose a reinforcement learning framework that allows for learned action valuations to be decomposed into effector-specific components when appropriate to a task, and test it by studying to what extent human behavior and blood oxygen level-dependent (BOLD) activity can exploit such a decomposition in a multieffector choice task. Subjects made simultaneous decisions with their left and right hands and received separate reward feedback for each hand movement. We found that choice behavior was better described by a learning model that decomposed the values of bimanual movements into separate values for each effector, rather than a traditional model that treated the bimanual actions as unitary with a single value. A decomposition of value into effector-specific components was also observed in value-related BOLD signaling, in the form of lateralized biases in striatal correlates of prediction error and anticipatory value correlates in the intraparietal sulcus. These results suggest that the human brain can use decomposed value representations to "divide and conquer" reinforcement learning over high-dimensional action spaces.

  6. Multi-agent system for Knowledge-based recommendation of Learning Objects

    Directory of Open Access Journals (Sweden)

    Paula Andrea RODRÍGUEZ MARÍN

    2015-12-01

    Full Text Available Learning Object (LO is a content unit being used within virtual learning environments, which -once found and retrieved- may assist students in the teaching - learning process. Such LO search and retrieval are recently supported and enhanced by data mining techniques. In this sense, clustering can be used to find groups holding similar LOs so that from obtained groups, knowledge-based recommender systems (KRS can recommend more adapted and relevant LOs. In particular, prior knowledge come from LOs previously selected, liked and ranked by the student to whom the recommendation will be performed. In this paper, we present a KRS for LOs, which uses a conventional clustering technique, namely K-means, aimed at finding similar LOs and delivering resources adapted to a specific student. Obtained promising results show that proposed KRS is able to both retrieve relevant LO and improve the recommendation precision.Learning Object (LO is a content unit being used within virtual learning environments, which -once found and retrieved- may assist students in the teaching - learning process. Such LO search and retrieval are recently supported and enhanced by data mining techniques. In this sense, clustering can be used to find groups holding similar LOs so that from obtained groups, knowledge-based recommender systems (KRS can recommend more adapted and relevant LOs. In particular, prior knowledge come from LOs previously selected, liked and ranked by the student to whom the recommendation will be performed. In this paper, we present a KRS for LOs, which uses a conventional clustering technique, namely K-means, aimed at finding similar LOs and delivering resources adapted to a specific student. Obtained promising results show that proposed KRS is able to both retrieve relevant LO and improve the recommendation precision.

  7. Reinforcement Learning in Distributed Domains: Beyond Team Games

    Science.gov (United States)

    Wolpert, David H.; Sill, Joseph; Turner, Kagan

    2000-01-01

    Distributed search algorithms are crucial in dealing with large optimization problems, particularly when a centralized approach is not only impractical but infeasible. Many machine learning concepts have been applied to search algorithms in order to improve their effectiveness. In this article we present an algorithm that blends Reinforcement Learning (RL) and hill climbing directly, by using the RL signal to guide the exploration step of a hill climbing algorithm. We apply this algorithm to the domain of a constellations of communication satellites where the goal is to minimize the loss of importance weighted data. We introduce the concept of 'ghost' traffic, where correctly setting this traffic induces the satellites to act to optimize the world utility. Our results indicated that the bi-utility search introduced in this paper outperforms both traditional hill climbing algorithms and distributed RL approaches such as team games.

  8. Forgetting in Reinforcement Learning Links Sustained Dopamine Signals to Motivation.

    Science.gov (United States)

    Kato, Ayaka; Morita, Kenji

    2016-10-01

    It has been suggested that dopamine (DA) represents reward-prediction-error (RPE) defined in reinforcement learning and therefore DA responds to unpredicted but not predicted reward. However, recent studies have found DA response sustained towards predictable reward in tasks involving self-paced behavior, and suggested that this response represents a motivational signal. We have previously shown that RPE can sustain if there is decay/forgetting of learned-values, which can be implemented as decay of synaptic strengths storing learned-values. This account, however, did not explain the suggested link between tonic/sustained DA and motivation. In the present work, we explored the motivational effects of the value-decay in self-paced approach behavior, modeled as a series of 'Go' or 'No-Go' selections towards a goal. Through simulations, we found that the value-decay can enhance motivation, specifically, facilitate fast goal-reaching, albeit counterintuitively. Mathematical analyses revealed that underlying potential mechanisms are twofold: (1) decay-induced sustained RPE creates a gradient of 'Go' values towards a goal, and (2) value-contrasts between 'Go' and 'No-Go' are generated because while chosen values are continually updated, unchosen values simply decay. Our model provides potential explanations for the key experimental findings that suggest DA's roles in motivation: (i) slowdown of behavior by post-training blockade of DA signaling, (ii) observations that DA blockade severely impairs effortful actions to obtain rewards while largely sparing seeking of easily obtainable rewards, and (iii) relationships between the reward amount, the level of motivation reflected in the speed of behavior, and the average level of DA. These results indicate that reinforcement learning with value-decay, or forgetting, provides a parsimonious mechanistic account for the DA's roles in value-learning and motivation. Our results also suggest that when biological systems for value-learning

  9. Forgetting in Reinforcement Learning Links Sustained Dopamine Signals to Motivation.

    Directory of Open Access Journals (Sweden)

    Ayaka Kato

    2016-10-01

    Full Text Available It has been suggested that dopamine (DA represents reward-prediction-error (RPE defined in reinforcement learning and therefore DA responds to unpredicted but not predicted reward. However, recent studies have found DA response sustained towards predictable reward in tasks involving self-paced behavior, and suggested that this response represents a motivational signal. We have previously shown that RPE can sustain if there is decay/forgetting of learned-values, which can be implemented as decay of synaptic strengths storing learned-values. This account, however, did not explain the suggested link between tonic/sustained DA and motivation. In the present work, we explored the motivational effects of the value-decay in self-paced approach behavior, modeled as a series of 'Go' or 'No-Go' selections towards a goal. Through simulations, we found that the value-decay can enhance motivation, specifically, facilitate fast goal-reaching, albeit counterintuitively. Mathematical analyses revealed that underlying potential mechanisms are twofold: (1 decay-induced sustained RPE creates a gradient of 'Go' values towards a goal, and (2 value-contrasts between 'Go' and 'No-Go' are generated because while chosen values are continually updated, unchosen values simply decay. Our model provides potential explanations for the key experimental findings that suggest DA's roles in motivation: (i slowdown of behavior by post-training blockade of DA signaling, (ii observations that DA blockade severely impairs effortful actions to obtain rewards while largely sparing seeking of easily obtainable rewards, and (iii relationships between the reward amount, the level of motivation reflected in the speed of behavior, and the average level of DA. These results indicate that reinforcement learning with value-decay, or forgetting, provides a parsimonious mechanistic account for the DA's roles in value-learning and motivation. Our results also suggest that when biological systems

  10. Reinforcement learning for dpm of embedded visual sensor nodes

    International Nuclear Information System (INIS)

    Khani, U.; Sadhayo, I. H.

    2014-01-01

    This paper proposes a RL (Reinforcement Learning) based DPM (Dynamic Power Management) technique to learn time out policies during a visual sensor node's operation which has multiple power/performance states. As opposed to the widely used static time out policies, our proposed DPM policy which is also referred to as OLTP (Online Learning of Time out Policies), learns to dynamically change the time out decisions in the different node states including the non-operational states. The selection of time out values in different power/performance states of a visual sensing platform is based on the workload estimates derived from a ML-ANN (Multi-Layer Artificial Neural Network) and an objective function given by weighted performance and power parameters. The DPM approach is also able to dynamically adjust the power-performance weights online to satisfy a given constraint of either power consumption or performance. Results show that the proposed learning algorithm explores the power-performance tradeoff with non-stationary workload and outperforms other DPM policies. It also performs the online adjustment of the tradeoff parameters in order to meet a user-specified constraint. (author)

  11. Explicit and implicit reinforcement learning across the psychosis spectrum.

    Science.gov (United States)

    Barch, Deanna M; Carter, Cameron S; Gold, James M; Johnson, Sheri L; Kring, Ann M; MacDonald, Angus W; Pizzagalli, Diego A; Ragland, J Daniel; Silverstein, Steven M; Strauss, Milton E

    2017-07-01

    Motivational and hedonic impairments are core features of a variety of types of psychopathology. An important aspect of motivational function is reinforcement learning (RL), including implicit (i.e., outside of conscious awareness) and explicit (i.e., including explicit representations about potential reward associations) learning, as well as both positive reinforcement (learning about actions that lead to reward) and punishment (learning to avoid actions that lead to loss). Here we present data from paradigms designed to assess both positive and negative components of both implicit and explicit RL, examine performance on each of these tasks among individuals with schizophrenia, schizoaffective disorder, and bipolar disorder with psychosis, and examine their relative relationships to specific symptom domains transdiagnostically. None of the diagnostic groups differed significantly from controls on the implicit RL tasks in either bias toward a rewarded response or bias away from a punished response. However, on the explicit RL task, both the individuals with schizophrenia and schizoaffective disorder performed significantly worse than controls, but the individuals with bipolar did not. Worse performance on the explicit RL task, but not the implicit RL task, was related to worse motivation and pleasure symptoms across all diagnostic categories. Performance on explicit RL, but not implicit RL, was related to working memory, which accounted for some of the diagnostic group differences. However, working memory did not account for the relationship of explicit RL to motivation and pleasure symptoms. These findings suggest transdiagnostic relationships across the spectrum of psychotic disorders between motivation and pleasure impairments and explicit RL. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

  12. Characterizing Reinforcement Learning Methods through Parameterized Learning Problems

    Science.gov (United States)

    2011-06-03

    extraneous. The agent could potentially adapt these representational aspects by applying methods from feature selection ( Kolter and Ng, 2009; Petrik et al...611–616. AAAI Press. Kolter , J. Z. and Ng, A. Y. (2009). Regularization and feature selection in least-squares temporal difference learning. In A. P

  13. Teachers Observe to Learn: Differences in Social Behavior of Toddlers and Preschoolers in Same-Age and Multiage Groupings

    Science.gov (United States)

    Logue, Mary Ellin

    2006-01-01

    This article presents an action research conducted by a group of teachers comparing multiage with same-age interactions of children, especially among toddlers. The research involving 31 children ranging in age from two through five-and-a-half was conducted under optimal conditions, with small groups, low teacher-child ratios, and highly trained…

  14. Self-Paced Prioritized Curriculum Learning With Coverage Penalty in Deep Reinforcement Learning.

    Science.gov (United States)

    Ren, Zhipeng; Dong, Daoyi; Li, Huaxiong; Chen, Chunlin; Zhipeng Ren; Daoyi Dong; Huaxiong Li; Chunlin Chen; Dong, Daoyi; Li, Huaxiong; Chen, Chunlin; Ren, Zhipeng

    2018-06-01

    In this paper, a new training paradigm is proposed for deep reinforcement learning using self-paced prioritized curriculum learning with coverage penalty. The proposed deep curriculum reinforcement learning (DCRL) takes the most advantage of experience replay by adaptively selecting appropriate transitions from replay memory based on the complexity of each transition. The criteria of complexity in DCRL consist of self-paced priority as well as coverage penalty. The self-paced priority reflects the relationship between the temporal-difference error and the difficulty of the current curriculum for sample efficiency. The coverage penalty is taken into account for sample diversity. With comparison to deep Q network (DQN) and prioritized experience replay (PER) methods, the DCRL algorithm is evaluated on Atari 2600 games, and the experimental results show that DCRL outperforms DQN and PER on most of these games. More results further show that the proposed curriculum training paradigm of DCRL is also applicable and effective for other memory-based deep reinforcement learning approaches, such as double DQN and dueling network. All the experimental results demonstrate that DCRL can achieve improved training efficiency and robustness for deep reinforcement learning.

  15. Ontological Modeling of Meta Learning Multi-Agent Systems in OWL-DL

    Czech Academy of Sciences Publication Activity Database

    Kazík, O.; Neruda, Roman

    2012-01-01

    Roč. 39, č. 4 (2012), s. 357-362 ISSN 1819-9224 R&D Projects: GA MŠk(CZ) ME10023 Grant - others:GA UK(CZ) 629612; UK(CZ) SVV-265314 Institutional support: RVO:67985807 Keywords : data mining * meta learning * roles * description logic * ontology Subject RIV: IN - Informatics, Computer Science http://www.iaeng.org/IJCS/issues_v39/issue_4/IJCS_39_4_04.pdf

  16. Empirical Centroid Fictitious Play: An Approach For Distributed Learning In Multi-Agent Games

    OpenAIRE

    Swenson, Brian; Kar, Soummya; Xavier, Joao

    2013-01-01

    The paper is concerned with distributed learning in large-scale games. The well-known fictitious play (FP) algorithm is addressed, which, despite theoretical convergence results, might be impractical to implement in large-scale settings due to intense computation and communication requirements. An adaptation of the FP algorithm, designated as the empirical centroid fictitious play (ECFP), is presented. In ECFP players respond to the centroid of all players' actions rather than track and respo...

  17. Deep reinforcement learning for automated radiation adaptation in lung cancer.

    Science.gov (United States)

    Tseng, Huan-Hsin; Luo, Yi; Cui, Sunan; Chien, Jen-Tzung; Ten Haken, Randall K; Naqa, Issam El

    2017-12-01

    To investigate deep reinforcement learning (DRL) based on historical treatment plans for developing automated radiation adaptation protocols for nonsmall cell lung cancer (NSCLC) patients that aim to maximize tumor local control at reduced rates of radiation pneumonitis grade 2 (RP2). In a retrospective population of 114 NSCLC patients who received radiotherapy, a three-component neural networks framework was developed for deep reinforcement learning (DRL) of dose fractionation adaptation. Large-scale patient characteristics included clinical, genetic, and imaging radiomics features in addition to tumor and lung dosimetric variables. First, a generative adversarial network (GAN) was employed to learn patient population characteristics necessary for DRL training from a relatively limited sample size. Second, a radiotherapy artificial environment (RAE) was reconstructed by a deep neural network (DNN) utilizing both original and synthetic data (by GAN) to estimate the transition probabilities for adaptation of personalized radiotherapy patients' treatment courses. Third, a deep Q-network (DQN) was applied to the RAE for choosing the optimal dose in a response-adapted treatment setting. This multicomponent reinforcement learning approach was benchmarked against real clinical decisions that were applied in an adaptive dose escalation clinical protocol. In which, 34 patients were treated based on avid PET signal in the tumor and constrained by a 17.2% normal tissue complication probability (NTCP) limit for RP2. The uncomplicated cure probability (P+) was used as a baseline reward function in the DRL. Taking our adaptive dose escalation protocol as a blueprint for the proposed DRL (GAN + RAE + DQN) architecture, we obtained an automated dose adaptation estimate for use at ∼2/3 of the way into the radiotherapy treatment course. By letting the DQN component freely control the estimated adaptive dose per fraction (ranging from 1-5 Gy), the DRL automatically favored dose

  18. Reinforcement Learning for Routing in Cognitive Radio Ad Hoc Networks

    Directory of Open Access Journals (Sweden)

    Hasan A. A. Al-Rawi

    2014-01-01

    Full Text Available Cognitive radio (CR enables unlicensed users (or secondary users, SUs to sense for and exploit underutilized licensed spectrum owned by the licensed users (or primary users, PUs. Reinforcement learning (RL is an artificial intelligence approach that enables a node to observe, learn, and make appropriate decisions on action selection in order to maximize network performance. Routing enables a source node to search for a least-cost route to its destination node. While there have been increasing efforts to enhance the traditional RL approach for routing in wireless networks, this research area remains largely unexplored in the domain of routing in CR networks. This paper applies RL in routing and investigates the effects of various features of RL (i.e., reward function, exploitation, and exploration, as well as learning rate through simulation. New approaches and recommendations are proposed to enhance the features in order to improve the network performance brought about by RL to routing. Simulation results show that the RL parameters of the reward function, exploitation, and exploration, as well as learning rate, must be well regulated, and the new approaches proposed in this paper improves SUs’ network performance without significantly jeopardizing PUs’ network performance, specifically SUs’ interference to PUs.

  19. Grounding the meanings in sensorimotor behavior using reinforcement learning

    Directory of Open Access Journals (Sweden)

    Igor eFarkaš

    2012-02-01

    Full Text Available The recent outburst of interest in cognitive developmental robotics is fueled by the ambition to propose ecologically plausible mechanisms of how, among other things, a learning agent/robot could ground linguistic meanings in its sensorimotor behaviour. Along this stream, we propose a model that allows the simulated iCub robot to learn the meanings of actions (point, touch and push oriented towards objects in robot's peripersonal space. In our experiments, the iCub learns to execute motor actions and comment on them. Architecturally, the model is composed of three neural-network-based modules that are trained in different ways. The first module, a two-layer perceptron, is trained by back-propagation to attend to the target position in the visual scene, given the low-level visual information and the feature-based target information. The second module, having the form of an actor-critic architecture, is the most distinguishing part of our model, and is trained by a continuous version of reinforcement learning to execute actions as sequences, based on a linguistic command. The third module, an echo-state network, is trained to provide the linguistic description of the executed actions. The trained model generalises well in case of novel action-target combinations with randomised initial arm positions. It can also promptly adapt its behavior if the action/target suddenly changes during motor execution.

  20. A Multi-Agent Control Architecture for a Robotic Wheelchair

    Directory of Open Access Journals (Sweden)

    C. Galindo

    2006-01-01

    Full Text Available Assistant robots like robotic wheelchairs can perform an effective and valuable work in our daily lives. However, they eventually may need external help from humans in the robot environment (particularly, the driver in the case of a wheelchair to accomplish safely and efficiently some tricky tasks for the current technology, i.e. opening a locked door, traversing a crowded area, etc. This article proposes a control architecture for assistant robots designed under a multi-agent perspective that facilitates the participation of humans into the robotic system and improves the overall performance of the robot as well as its dependability. Within our design, agents have their own intentions and beliefs, have different abilities (that include algorithmic behaviours and human skills and also learn autonomously the most convenient method to carry out their actions through reinforcement learning. The proposed architecture is illustrated with a real assistant robot: a robotic wheelchair that provides mobility to impaired or elderly people.

  1. Learning User Preferences in Ubiquitous Systems: A User Study and a Reinforcement Learning Approach

    OpenAIRE

    Zaidenberg , Sofia; Reignier , Patrick; Mandran , Nadine

    2010-01-01

    International audience; Our study concerns a virtual assistant, proposing services to the user based on its current perceived activity and situation (ambient intelligence). Instead of asking the user to define his preferences, we acquire them automatically using a reinforcement learning approach. Experiments showed that our system succeeded the learning of user preferences. In order to validate the relevance and usability of such a system, we have first conducted a user study. 26 non-expert s...

  2. Learning to Run challenge solutions: Adapting reinforcement learning methods for neuromusculoskeletal environments

    OpenAIRE

    Kidziński, Łukasz; Mohanty, Sharada Prasanna; Ong, Carmichael; Huang, Zhewei; Zhou, Shuchang; Pechenko, Anton; Stelmaszczyk, Adam; Jarosik, Piotr; Pavlov, Mikhail; Kolesnikov, Sergey; Plis, Sergey; Chen, Zhibo; Zhang, Zhizheng; Chen, Jiale; Shi, Jun

    2018-01-01

    In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement learning approaches, based on algorithms such as Deep Deterministic Policy Gradient, Proximal Policy Optimization, and Trust Region Policy Optimization. Many solutions use similar ...

  3. Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing

    NARCIS (Netherlands)

    Le, M.N.; Fokkens, A.S.

    Error propagation is a common problem in NLP. Reinforcement learning explores erroneous states during training and can therefore be more robust when mistakes are made early in a process. In this paper, we apply reinforcement learning to greedy dependency parsing which is known to suffer from error

  4. A Distributed Multi-Agent System for Collaborative Information Management and Learning

    Science.gov (United States)

    Chen, James R.; Wolfe, Shawn R.; Wragg, Stephen D.; Koga, Dennis (Technical Monitor)

    2000-01-01

    In this paper, we present DIAMS, a system of distributed, collaborative agents to help users access, manage, share and exchange information. A DIAMS personal agent helps its owner find information most relevant to current needs. It provides tools and utilities for users to manage their information repositories with dynamic organization and virtual views. Flexible hierarchical display is integrated with indexed query search-to support effective information access. Automatic indexing methods are employed to support user queries and communication between agents. Contents of a repository are kept in object-oriented storage to facilitate information sharing. Collaboration between users is aided by easy sharing utilities as well as automated information exchange. Matchmaker agents are designed to establish connections between users with similar interests and expertise. DIAMS agents provide needed services for users to share and learn information from one another on the World Wide Web.

  5. Working Memory and Reinforcement Schedule Jointly Determine Reinforcement Learning in Children: Potential Implications for Behavioral Parent Training

    Directory of Open Access Journals (Sweden)

    Elien Segers

    2018-03-01

    Full Text Available Introduction: Behavioral Parent Training (BPT is often provided for childhood psychiatric disorders. These disorders have been shown to be associated with working memory impairments. BPT is based on operant learning principles, yet how operant principles shape behavior (through the partial reinforcement (PRF extinction effect, i.e., greater resistance to extinction that is created when behavior is reinforced partially rather than continuously and the potential role of working memory therein is scarcely studied in children. This study explored the PRF extinction effect and the role of working memory therein using experimental tasks in typically developing children.Methods: Ninety-seven children (age 6–10 completed a working memory task and an operant learning task, in which children acquired a response-sequence rule under either continuous or PRF (120 trials, followed by an extinction phase (80 trials. Data of 88 children were used for analysis.Results: The PRF extinction effect was confirmed: We observed slower acquisition and extinction in the PRF condition as compared to the continuous reinforcement (CRF condition. Working memory was negatively related to acquisition but not extinction performance.Conclusion: Both reinforcement contingencies and working memory relate to acquisition performance. Potential implications for BPT are that decreasing working memory load may enhance the chance of optimally learning through reinforcement.

  6. Curiosity driven reinforcement learning for motion planning on humanoids

    Science.gov (United States)

    Frank, Mikhail; Leitner, Jürgen; Stollenga, Marijn; Förster, Alexander; Schmidhuber, Jürgen

    2014-01-01

    Most previous work on artificial curiosity (AC) and intrinsic motivation focuses on basic concepts and theory. Experimental results are generally limited to toy scenarios, such as navigation in a simulated maze, or control of a simple mechanical system with one or two degrees of freedom. To study AC in a more realistic setting, we embody a curious agent in the complex iCub humanoid robot. Our novel reinforcement learning (RL) framework consists of a state-of-the-art, low-level, reactive control layer, which controls the iCub while respecting constraints, and a high-level curious agent, which explores the iCub's state-action space through information gain maximization, learning a world model from experience, controlling the actual iCub hardware in real-time. To the best of our knowledge, this is the first ever embodied, curious agent for real-time motion planning on a humanoid. We demonstrate that it can learn compact Markov models to represent large regions of the iCub's configuration space, and that the iCub explores intelligently, showing interest in its physical constraints as well as in objects it finds in its environment. PMID:24432001

  7. How we learn to make decisions: rapid propagation of reinforcement learning prediction errors in humans.

    Science.gov (United States)

    Krigolson, Olav E; Hassall, Cameron D; Handy, Todd C

    2014-03-01

    Our ability to make decisions is predicated upon our knowledge of the outcomes of the actions available to us. Reinforcement learning theory posits that actions followed by a reward or punishment acquire value through the computation of prediction errors-discrepancies between the predicted and the actual reward. A multitude of neuroimaging studies have demonstrated that rewards and punishments evoke neural responses that appear to reflect reinforcement learning prediction errors [e.g., Krigolson, O. E., Pierce, L. J., Holroyd, C. B., & Tanaka, J. W. Learning to become an expert: Reinforcement learning and the acquisition of perceptual expertise. Journal of Cognitive Neuroscience, 21, 1833-1840, 2009; Bayer, H. M., & Glimcher, P. W. Midbrain dopamine neurons encode a quantitative reward prediction error signal. Neuron, 47, 129-141, 2005; O'Doherty, J. P. Reward representations and reward-related learning in the human brain: Insights from neuroimaging. Current Opinion in Neurobiology, 14, 769-776, 2004; Holroyd, C. B., & Coles, M. G. H. The neural basis of human error processing: Reinforcement learning, dopamine, and the error-related negativity. Psychological Review, 109, 679-709, 2002]. Here, we used the brain ERP technique to demonstrate that not only do rewards elicit a neural response akin to a prediction error but also that this signal rapidly diminished and propagated to the time of choice presentation with learning. Specifically, in a simple, learnable gambling task, we show that novel rewards elicited a feedback error-related negativity that rapidly decreased in amplitude with learning. Furthermore, we demonstrate the existence of a reward positivity at choice presentation, a previously unreported ERP component that has a similar timing and topography as the feedback error-related negativity that increased in amplitude with learning. The pattern of results we observed mirrored the output of a computational model that we implemented to compute reward

  8. Memory Transformation Enhances Reinforcement Learning in Dynamic Environments.

    Science.gov (United States)

    Santoro, Adam; Frankland, Paul W; Richards, Blake A

    2016-11-30

    Over the course of systems consolidation, there is a switch from a reliance on detailed episodic memories to generalized schematic memories. This switch is sometimes referred to as "memory transformation." Here we demonstrate a previously unappreciated benefit of memory transformation, namely, its ability to enhance reinforcement learning in a dynamic environment. We developed a neural network that is trained to find rewards in a foraging task where reward locations are continuously changing. The network can use memories for specific locations (episodic memories) and statistical patterns of locations (schematic memories) to guide its search. We find that switching from an episodic to a schematic strategy over time leads to enhanced performance due to the tendency for the reward location to be highly correlated with itself in the short-term, but regress to a stable distribution in the long-term. We also show that the statistics of the environment determine the optimal utilization of both types of memory. Our work recasts the theoretical question of why memory transformation occurs, shifting the focus from the avoidance of memory interference toward the enhancement of reinforcement learning across multiple timescales. As time passes, memories transform from a highly detailed state to a more gist-like state, in a process called "memory transformation." Theories of memory transformation speak to its advantages in terms of reducing memory interference, increasing memory robustness, and building models of the environment. However, the role of memory transformation from the perspective of an agent that continuously acts and receives reward in its environment is not well explored. In this work, we demonstrate a view of memory transformation that defines it as a way of optimizing behavior across multiple timescales. Copyright © 2016 the authors 0270-6474/16/3612228-15$15.00/0.

  9. GA-based fuzzy reinforcement learning for control of a magnetic bearing system.

    Science.gov (United States)

    Lin, C T; Jou, C P

    2000-01-01

    This paper proposes a TD (temporal difference) and GA (genetic algorithm)-based reinforcement (TDGAR) learning method and applies it to the control of a real magnetic bearing system. The TDGAR learning scheme is a new hybrid GA, which integrates the TD prediction method and the GA to perform the reinforcement learning task. The TDGAR learning system is composed of two integrated feedforward networks. One neural network acts as a critic network to guide the learning of the other network (the action network) which determines the outputs (actions) of the TDGAR learning system. The action network can be a normal neural network or a neural fuzzy network. Using the TD prediction method, the critic network can predict the external reinforcement signal and provide a more informative internal reinforcement signal to the action network. The action network uses the GA to adapt itself according to the internal reinforcement signal. The key concept of the TDGAR learning scheme is to formulate the internal reinforcement signal as the fitness function for the GA such that the GA can evaluate the candidate solutions (chromosomes) regularly, even during periods without external feedback from the environment. This enables the GA to proceed to new generations regularly without waiting for the arrival of the external reinforcement signal. This can usually accelerate the GA learning since a reinforcement signal may only be available at a time long after a sequence of actions has occurred in the reinforcement learning problem. The proposed TDGAR learning system has been used to control an active magnetic bearing (AMB) system in practice. A systematic design procedure is developed to achieve successful integration of all the subsystems including magnetic suspension, mechanical structure, and controller training. The results show that the TDGAR learning scheme can successfully find a neural controller or a neural fuzzy controller for a self-designed magnetic bearing system.

  10. Reinforcement learning techniques for controlling resources in power networks

    Science.gov (United States)

    Kowli, Anupama Sunil

    As power grids transition towards increased reliance on renewable generation, energy storage and demand response resources, an effective control architecture is required to harness the full functionalities of these resources. There is a critical need for control techniques that recognize the unique characteristics of the different resources and exploit the flexibility afforded by them to provide ancillary services to the grid. The work presented in this dissertation addresses these needs. Specifically, new algorithms are proposed, which allow control synthesis in settings wherein the precise distribution of the uncertainty and its temporal statistics are not known. These algorithms are based on recent developments in Markov decision theory, approximate dynamic programming and reinforcement learning. They impose minimal assumptions on the system model and allow the control to be "learned" based on the actual dynamics of the system. Furthermore, they can accommodate complex constraints such as capacity and ramping limits on generation resources, state-of-charge constraints on storage resources, comfort-related limitations on demand response resources and power flow limits on transmission lines. Numerical studies demonstrating applications of these algorithms to practical control problems in power systems are discussed. Results demonstrate how the proposed control algorithms can be used to improve the performance and reduce the computational complexity of the economic dispatch mechanism in a power network. We argue that the proposed algorithms are eminently suitable to develop operational decision-making tools for large power grids with many resources and many sources of uncertainty.

  11. A Reinforcement Learning Framework for Spiking Networks with Dynamic Synapses

    Directory of Open Access Journals (Sweden)

    Karim El-Laithy

    2011-01-01

    Full Text Available An integration of both the Hebbian-based and reinforcement learning (RL rules is presented for dynamic synapses. The proposed framework permits the Hebbian rule to update the hidden synaptic model parameters regulating the synaptic response rather than the synaptic weights. This is performed using both the value and the sign of the temporal difference in the reward signal after each trial. Applying this framework, a spiking network with spike-timing-dependent synapses is tested to learn the exclusive-OR computation on a temporally coded basis. Reward values are calculated with the distance between the output spike train of the network and a reference target one. Results show that the network is able to capture the required dynamics and that the proposed framework can reveal indeed an integrated version of Hebbian and RL. The proposed framework is tractable and less computationally expensive. The framework is applicable to a wide class of synaptic models and is not restricted to the used neural representation. This generality, along with the reported results, supports adopting the introduced approach to benefit from the biologically plausible synaptic models in a wide range of intuitive signal processing.

  12. A reinforcement learning model of joy, distress, hope and fear

    Science.gov (United States)

    Broekens, Joost; Jacobs, Elmer; Jonker, Catholijn M.

    2015-07-01

    In this paper we computationally study the relation between adaptive behaviour and emotion. Using the reinforcement learning framework, we propose that learned state utility, ?, models fear (negative) and hope (positive) based on the fact that both signals are about anticipation of loss or gain. Further, we propose that joy/distress is a signal similar to the error signal. We present agent-based simulation experiments that show that this model replicates psychological and behavioural dynamics of emotion. This work distinguishes itself by assessing the dynamics of emotion in an adaptive agent framework - coupling it to the literature on habituation, development, extinction and hope theory. Our results support the idea that the function of emotion is to provide a complex feedback signal for an organism to adapt its behaviour. Our work is relevant for understanding the relation between emotion and adaptation in animals, as well as for human-robot interaction, in particular how emotional signals can be used to communicate between adaptive agents and humans.

  13. Reinforcement Learning for Predictive Analytics in Smart Cities

    Directory of Open Access Journals (Sweden)

    Kostas Kolomvatsos

    2017-06-01

    Full Text Available The digitization of our lives cause a shift in the data production as well as in the required data management. Numerous nodes are capable of producing huge volumes of data in our everyday activities. Sensors, personal smart devices as well as the Internet of Things (IoT paradigm lead to a vast infrastructure that covers all the aspects of activities in modern societies. In the most of the cases, the critical issue for public authorities (usually, local, like municipalities is the efficient management of data towards the support of novel services. The reason is that analytics provided on top of the collected data could help in the delivery of new applications that will facilitate citizens’ lives. However, the provision of analytics demands intelligent techniques for the underlying data management. The most known technique is the separation of huge volumes of data into a number of parts and their parallel management to limit the required time for the delivery of analytics. Afterwards, analytics requests in the form of queries could be realized and derive the necessary knowledge for supporting intelligent applications. In this paper, we define the concept of a Query Controller ( Q C that receives queries for analytics and assigns each of them to a processor placed in front of each data partition. We discuss an intelligent process for query assignments that adopts Machine Learning (ML. We adopt two learning schemes, i.e., Reinforcement Learning (RL and clustering. We report on the comparison of the two schemes and elaborate on their combination. Our aim is to provide an efficient framework to support the decision making of the QC that should swiftly select the appropriate processor for each query. We provide mathematical formulations for the discussed problem and present simulation results. Through a comprehensive experimental evaluation, we reveal the advantages of the proposed models and describe the outcomes results while comparing them with a

  14. Longitudinal investigation on learned helplessness tested under negative and positive reinforcement involving stimulus control.

    Science.gov (United States)

    Oliveira, Emileane C; Hunziker, Maria Helena

    2014-07-01

    In this study, we investigated whether (a) animals demonstrating the learned helplessness effect during an escape contingency also show learning deficits under positive reinforcement contingencies involving stimulus control and (b) the exposure to positive reinforcement contingencies eliminates the learned helplessness effect under an escape contingency. Rats were initially exposed to controllable (C), uncontrollable (U) or no (N) shocks. After 24h, they were exposed to 60 escapable shocks delivered in a shuttlebox. In the following phase, we selected from each group the four subjects that presented the most typical group pattern: no escape learning (learned helplessness effect) in Group U and escape learning in Groups C and N. All subjects were then exposed to two phases, the (1) positive reinforcement for lever pressing under a multiple FR/Extinction schedule and (2) a re-test under negative reinforcement (escape). A fourth group (n=4) was exposed only to the positive reinforcement sessions. All subjects showed discrimination learning under multiple schedule. In the escape re-test, the learned helplessness effect was maintained for three of the animals in Group U. These results suggest that the learned helplessness effect did not extend to discriminative behavior that is positively reinforced and that the learned helplessness effect did not revert for most subjects after exposure to positive reinforcement. We discuss some theoretical implications as related to learned helplessness as an effect restricted to aversive contingencies and to the absence of reversion after positive reinforcement. This article is part of a Special Issue entitled: insert SI title. Copyright © 2014. Published by Elsevier B.V.

  15. Reinforcement Learning Based Novel Adaptive Learning Framework for Smart Grid Prediction

    Directory of Open Access Journals (Sweden)

    Tian Li

    2017-01-01

    Full Text Available Smart grid is a potential infrastructure to supply electricity demand for end users in a safe and reliable manner. With the rapid increase of the share of renewable energy and controllable loads in smart grid, the operation uncertainty of smart grid has increased briskly during recent years. The forecast is responsible for the safety and economic operation of the smart grid. However, most existing forecast methods cannot account for the smart grid due to the disabilities to adapt to the varying operational conditions. In this paper, reinforcement learning is firstly exploited to develop an online learning framework for the smart grid. With the capability of multitime scale resolution, wavelet neural network has been adopted in the online learning framework to yield reinforcement learning and wavelet neural network (RLWNN based adaptive learning scheme. The simulations on two typical prediction problems in smart grid, including wind power prediction and load forecast, validate the effectiveness and the scalability of the proposed RLWNN based learning framework and algorithm.

  16. The combination of appetitive and aversive reinforcers and the nature of their interaction during auditory learning.

    Science.gov (United States)

    Ilango, A; Wetzel, W; Scheich, H; Ohl, F W

    2010-03-31

    Learned changes in behavior can be elicited by either appetitive or aversive reinforcers. It is, however, not clear whether the two types of motivation, (approaching appetitive stimuli and avoiding aversive stimuli) drive learning in the same or different ways, nor is their interaction understood in situations where the two types are combined in a single experiment. To investigate this question we have developed a novel learning paradigm for Mongolian gerbils, which not only allows rewards and punishments to be presented in isolation or in combination with each other, but also can use these opposite reinforcers to drive the same learned behavior. Specifically, we studied learning of tone-conditioned hurdle crossing in a shuttle box driven by either an appetitive reinforcer (brain stimulation reward) or an aversive reinforcer (electrical footshock), or by a combination of both. Combination of the two reinforcers potentiated speed of acquisition, led to maximum possible performance, and delayed extinction as compared to either reinforcer alone. Additional experiments, using partial reinforcement protocols and experiments in which one of the reinforcers was omitted after the animals had been previously trained with the combination of both reinforcers, indicated that appetitive and aversive reinforcers operated together but acted in different ways: in this particular experimental context, punishment appeared to be more effective for initial acquisition and reward more effective to maintain a high level of conditioned responses (CRs). The results imply that learning mechanisms in problem solving were maximally effective when the initial punishment of mistakes was combined with the subsequent rewarding of correct performance. Copyright 2010 IBRO. Published by Elsevier Ltd. All rights reserved.

  17. Dopamine-Dependent Reinforcement of Motor Skill Learning: Evidence from Gilles de la Tourette Syndrome

    Science.gov (United States)

    Palminteri, Stefano; Lebreton, Mael; Worbe, Yulia; Hartmann, Andreas; Lehericy, Stephane; Vidailhet, Marie; Grabli, David; Pessiglione, Mathias

    2011-01-01

    Reinforcement learning theory has been extensively used to understand the neural underpinnings of instrumental behaviour. A central assumption surrounds dopamine signalling reward prediction errors, so as to update action values and ensure better choices in the future. However, educators may share the intuitive idea that reinforcements not only…

  18. Efficient collective swimming by harnessing vortices through deep reinforcement learning.

    Science.gov (United States)

    Verma, Siddhartha; Novati, Guido; Koumoutsakos, Petros

    2018-06-05

    Fish in schooling formations navigate complex flow fields replete with mechanical energy in the vortex wakes of their companions. Their schooling behavior has been associated with evolutionary advantages including energy savings, yet the underlying physical mechanisms remain unknown. We show that fish can improve their sustained propulsive efficiency by placing themselves in appropriate locations in the wake of other swimmers and intercepting judiciously their shed vortices. This swimming strategy leads to collective energy savings and is revealed through a combination of high-fidelity flow simulations with a deep reinforcement learning (RL) algorithm. The RL algorithm relies on a policy defined by deep, recurrent neural nets, with long-short-term memory cells, that are essential for capturing the unsteadiness of the two-way interactions between the fish and the vortical flow field. Surprisingly, we find that swimming in-line with a leader is not associated with energetic benefits for the follower. Instead, "smart swimmer(s)" place themselves at off-center positions, with respect to the axis of the leader(s) and deform their body to synchronize with the momentum of the oncoming vortices, thus enhancing their swimming efficiency at no cost to the leader(s). The results confirm that fish may harvest energy deposited in vortices and support the conjecture that swimming in formation is energetically advantageous. Moreover, this study demonstrates that deep RL can produce navigation algorithms for complex unsteady and vortical flow fields, with promising implications for energy savings in autonomous robotic swarms.

  19. Off-policy reinforcement learning for H∞ control design.

    Science.gov (United States)

    Luo, Biao; Wu, Huai-Ning; Huang, Tingwen

    2015-01-01

    The H∞ control design problem is considered for nonlinear systems with unknown internal system model. It is known that the nonlinear H∞ control problem can be transformed into solving the so-called Hamilton-Jacobi-Isaacs (HJI) equation, which is a nonlinear partial differential equation that is generally impossible to be solved analytically. Even worse, model-based approaches cannot be used for approximately solving HJI equation, when the accurate system model is unavailable or costly to obtain in practice. To overcome these difficulties, an off-policy reinforcement leaning (RL) method is introduced to learn the solution of HJI equation from real system data instead of mathematical system model, and its convergence is proved. In the off-policy RL method, the system data can be generated with arbitrary policies rather than the evaluating policy, which is extremely important and promising for practical systems. For implementation purpose, a neural network (NN)-based actor-critic structure is employed and a least-square NN weight update algorithm is derived based on the method of weighted residuals. Finally, the developed NN-based off-policy RL method is tested on a linear F16 aircraft plant, and further applied to a rotational/translational actuator system.

  20. Joint Extraction of Entities and Relations Using Reinforcement Learning and Deep Learning

    Directory of Open Access Journals (Sweden)

    Yuntian Feng

    2017-01-01

    Full Text Available We use both reinforcement learning and deep learning to simultaneously extract entities and relations from unstructured texts. For reinforcement learning, we model the task as a two-step decision process. Deep learning is used to automatically capture the most important information from unstructured texts, which represent the state in the decision process. By designing the reward function per step, our proposed method can pass the information of entity extraction to relation extraction and obtain feedback in order to extract entities and relations simultaneously. Firstly, we use bidirectional LSTM to model the context information, which realizes preliminary entity extraction. On the basis of the extraction results, attention based method can represent the sentences that include target entity pair to generate the initial state in the decision process. Then we use Tree-LSTM to represent relation mentions to generate the transition state in the decision process. Finally, we employ Q-Learning algorithm to get control policy π in the two-step decision process. Experiments on ACE2005 demonstrate that our method attains better performance than the state-of-the-art method and gets a 2.4% increase in recall-score.

  1. Joint Extraction of Entities and Relations Using Reinforcement Learning and Deep Learning.

    Science.gov (United States)

    Feng, Yuntian; Zhang, Hongjun; Hao, Wenning; Chen, Gang

    2017-01-01

    We use both reinforcement learning and deep learning to simultaneously extract entities and relations from unstructured texts. For reinforcement learning, we model the task as a two-step decision process. Deep learning is used to automatically capture the most important information from unstructured texts, which represent the state in the decision process. By designing the reward function per step, our proposed method can pass the information of entity extraction to relation extraction and obtain feedback in order to extract entities and relations simultaneously. Firstly, we use bidirectional LSTM to model the context information, which realizes preliminary entity extraction. On the basis of the extraction results, attention based method can represent the sentences that include target entity pair to generate the initial state in the decision process. Then we use Tree-LSTM to represent relation mentions to generate the transition state in the decision process. Finally, we employ Q -Learning algorithm to get control policy π in the two-step decision process. Experiments on ACE2005 demonstrate that our method attains better performance than the state-of-the-art method and gets a 2.4% increase in recall-score.

  2. Knowledge-Based Reinforcement Learning for Data Mining

    Science.gov (United States)

    Kudenko, Daniel; Grzes, Marek

    Data Mining is the process of extracting patterns from data. Two general avenues of research in the intersecting areas of agents and data mining can be distinguished. The first approach is concerned with mining an agent’s observation data in order to extract patterns, categorize environment states, and/or make predictions of future states. In this setting, data is normally available as a batch, and the agent’s actions and goals are often independent of the data mining task. The data collection is mainly considered as a side effect of the agent’s activities. Machine learning techniques applied in such situations fall into the class of supervised learning. In contrast, the second scenario occurs where an agent is actively performing the data mining, and is responsible for the data collection itself. For example, a mobile network agent is acquiring and processing data (where the acquisition may incur a certain cost), or a mobile sensor agent is moving in a (perhaps hostile) environment, collecting and processing sensor readings. In these settings, the tasks of the agent and the data mining are highly intertwined and interdependent (or even identical). Supervised learning is not a suitable technique for these cases. Reinforcement Learning (RL) enables an agent to learn from experience (in form of reward and punishment for explorative actions) and adapt to new situations, without a teacher. RL is an ideal learning technique for these data mining scenarios, because it fits the agent paradigm of continuous sensing and acting, and the RL agent is able to learn to make decisions on the sampling of the environment which provides the data. Nevertheless, RL still suffers from scalability problems, which have prevented its successful use in many complex real-world domains. The more complex the tasks, the longer it takes a reinforcement learning algorithm to converge to a good solution. For many real-world tasks, human expert knowledge is available. For example, human

  3. Nonparametric bayesian reward segmentation for skill discovery using inverse reinforcement learning

    CSIR Research Space (South Africa)

    Ranchod, P

    2015-10-01

    Full Text Available We present a method for segmenting a set of unstructured demonstration trajectories to discover reusable skills using inverse reinforcement learning (IRL). Each skill is characterised by a latent reward function which the demonstrator is assumed...

  4. Perception-based Co-evolutionary Reinforcement Learning for UAV Sensor Allocation

    National Research Council Canada - National Science Library

    Berenji, Hamid

    2003-01-01

    .... A Perception-based reasoning approach based on co-evolutionary reinforcement learning was developed for jointly addressing sensor allocation on each individual UAV and allocation of a team of UAVs...

  5. Applying reinforcement learning to the weapon assignment problem in air defence

    CSIR Research Space (South Africa)

    Mouton, H

    2011-12-01

    Full Text Available . The techniques investigated in this article were two methods from the machine-learning subfield of reinforcement learning (RL), namely a Monte Carlo (MC) control algorithm with exploring starts (MCES), and an off-policy temporal-difference (TD) learning...

  6. Place preference and vocal learning rely on distinct reinforcers in songbirds.

    Science.gov (United States)

    Murdoch, Don; Chen, Ruidong; Goldberg, Jesse H

    2018-04-30

    In reinforcement learning (RL) agents are typically tasked with maximizing a single objective function such as reward. But it remains poorly understood how agents might pursue distinct objectives at once. In machines, multiobjective RL can be achieved by dividing a single agent into multiple sub-agents, each of which is shaped by agent-specific reinforcement, but it remains unknown if animals adopt this strategy. Here we use songbirds to test if navigation and singing, two behaviors with distinct objectives, can be differentially reinforced. We demonstrate that strobe flashes aversively condition place preference but not song syllables. Brief noise bursts aversively condition song syllables but positively reinforce place preference. Thus distinct behavior-generating systems, or agencies, within a single animal can be shaped by correspondingly distinct reinforcement signals. Our findings suggest that spatially segregated vocal circuits can solve a credit assignment problem associated with multiobjective learning.

  7. A Reinforcement-Based Learning Paradigm Increases Anatomical Learning and Retention—A Neuroeducation Study

    Science.gov (United States)

    Anderson, Sarah J.; Hecker, Kent G.; Krigolson, Olave E.; Jamniczky, Heather A.

    2018-01-01

    In anatomy education, a key hurdle to engaging in higher-level discussion in the classroom is recognizing and understanding the extensive terminology used to identify and describe anatomical structures. Given the time-limited classroom environment, seeking methods to impart this foundational knowledge to students in an efficient manner is essential. Just-in-Time Teaching (JiTT) methods incorporate pre-class exercises (typically online) meant to establish foundational knowledge in novice learners so subsequent instructor-led sessions can focus on deeper, more complex concepts. Determining how best do we design and assess pre-class exercises requires a detailed examination of learning and retention in an applied educational context. Here we used electroencephalography (EEG) as a quantitative dependent variable to track learning and examine the efficacy of JiTT activities to teach anatomy. Specifically, we examined changes in the amplitude of the N250 and reward positivity event-related brain potential (ERP) components alongside behavioral performance as novice students participated in a series of computerized reinforcement-based learning modules to teach neuroanatomical structures. We found that as students learned to identify anatomical structures, the amplitude of the N250 increased and reward positivity amplitude decreased in response to positive feedback. Both on a retention and transfer exercise when learners successfully remembered and translated their knowledge to novel images, the amplitude of the reward positivity remained decreased compared to early learning. Our findings suggest ERPs can be used as a tool to track learning, retention, and transfer of knowledge and that employing the reinforcement learning paradigm is an effective educational approach for developing anatomical expertise. PMID:29467638

  8. A Reinforcement-Based Learning Paradigm Increases Anatomical Learning and Retention-A Neuroeducation Study.

    Science.gov (United States)

    Anderson, Sarah J; Hecker, Kent G; Krigolson, Olave E; Jamniczky, Heather A

    2018-01-01

    In anatomy education, a key hurdle to engaging in higher-level discussion in the classroom is recognizing and understanding the extensive terminology used to identify and describe anatomical structures. Given the time-limited classroom environment, seeking methods to impart this foundational knowledge to students in an efficient manner is essential. Just-in-Time Teaching (JiTT) methods incorporate pre-class exercises (typically online) meant to establish foundational knowledge in novice learners so subsequent instructor-led sessions can focus on deeper, more complex concepts. Determining how best do we design and assess pre-class exercises requires a detailed examination of learning and retention in an applied educational context. Here we used electroencephalography (EEG) as a quantitative dependent variable to track learning and examine the efficacy of JiTT activities to teach anatomy. Specifically, we examined changes in the amplitude of the N250 and reward positivity event-related brain potential (ERP) components alongside behavioral performance as novice students participated in a series of computerized reinforcement-based learning modules to teach neuroanatomical structures. We found that as students learned to identify anatomical structures, the amplitude of the N250 increased and reward positivity amplitude decreased in response to positive feedback. Both on a retention and transfer exercise when learners successfully remembered and translated their knowledge to novel images, the amplitude of the reward positivity remained decreased compared to early learning. Our findings suggest ERPs can be used as a tool to track learning, retention, and transfer of knowledge and that employing the reinforcement learning paradigm is an effective educational approach for developing anatomical expertise.

  9. A Reinforcement-Based Learning Paradigm Increases Anatomical Learning and Retention—A Neuroeducation Study

    Directory of Open Access Journals (Sweden)

    Sarah J. Anderson

    2018-02-01

    Full Text Available In anatomy education, a key hurdle to engaging in higher-level discussion in the classroom is recognizing and understanding the extensive terminology used to identify and describe anatomical structures. Given the time-limited classroom environment, seeking methods to impart this foundational knowledge to students in an efficient manner is essential. Just-in-Time Teaching (JiTT methods incorporate pre-class exercises (typically online meant to establish foundational knowledge in novice learners so subsequent instructor-led sessions can focus on deeper, more complex concepts. Determining how best do we design and assess pre-class exercises requires a detailed examination of learning and retention in an applied educational context. Here we used electroencephalography (EEG as a quantitative dependent variable to track learning and examine the efficacy of JiTT activities to teach anatomy. Specifically, we examined changes in the amplitude of the N250 and reward positivity event-related brain potential (ERP components alongside behavioral performance as novice students participated in a series of computerized reinforcement-based learning modules to teach neuroanatomical structures. We found that as students learned to identify anatomical structures, the amplitude of the N250 increased and reward positivity amplitude decreased in response to positive feedback. Both on a retention and transfer exercise when learners successfully remembered and translated their knowledge to novel images, the amplitude of the reward positivity remained decreased compared to early learning. Our findings suggest ERPs can be used as a tool to track learning, retention, and transfer of knowledge and that employing the reinforcement learning paradigm is an effective educational approach for developing anatomical expertise.

  10. Identification of animal behavioral strategies by inverse reinforcement learning.

    Directory of Open Access Journals (Sweden)

    Shoichiro Yamaguchi

    2018-05-01

    Full Text Available Animals are able to reach a desired state in an environment by controlling various behavioral patterns. Identification of the behavioral strategy used for this control is important for understanding animals' decision-making and is fundamental to dissect information processing done by the nervous system. However, methods for quantifying such behavioral strategies have not been fully established. In this study, we developed an inverse reinforcement-learning (IRL framework to identify an animal's behavioral strategy from behavioral time-series data. We applied this framework to C. elegans thermotactic behavior; after cultivation at a constant temperature with or without food, fed worms prefer, while starved worms avoid the cultivation temperature on a thermal gradient. Our IRL approach revealed that the fed worms used both the absolute temperature and its temporal derivative and that their behavior involved two strategies: directed migration (DM and isothermal migration (IM. With DM, worms efficiently reached specific temperatures, which explains their thermotactic behavior when fed. With IM, worms moved along a constant temperature, which reflects isothermal tracking, well-observed in previous studies. In contrast to fed animals, starved worms escaped the cultivation temperature using only the absolute, but not the temporal derivative of temperature. We also investigated the neural basis underlying these strategies, by applying our method to thermosensory neuron-deficient worms. Thus, our IRL-based approach is useful in identifying animal strategies from behavioral time-series data and could be applied to a wide range of behavioral studies, including decision-making, in other organisms.

  11. Optimized Assistive Human-Robot Interaction Using Reinforcement Learning.

    Science.gov (United States)

    Modares, Hamidreza; Ranatunga, Isura; Lewis, Frank L; Popa, Dan O

    2016-03-01

    An intelligent human-robot interaction (HRI) system with adjustable robot behavior is presented. The proposed HRI system assists the human operator to perform a given task with minimum workload demands and optimizes the overall human-robot system performance. Motivated by human factor studies, the presented control structure consists of two control loops. First, a robot-specific neuro-adaptive controller is designed in the inner loop to make the unknown nonlinear robot behave like a prescribed robot impedance model as perceived by a human operator. In contrast to existing neural network and adaptive impedance-based control methods, no information of the task performance or the prescribed robot impedance model parameters is required in the inner loop. Then, a task-specific outer-loop controller is designed to find the optimal parameters of the prescribed robot impedance model to adjust the robot's dynamics to the operator skills and minimize the tracking error. The outer loop includes the human operator, the robot, and the task performance details. The problem of finding the optimal parameters of the prescribed robot impedance model is transformed into a linear quadratic regulator (LQR) problem which minimizes the human effort and optimizes the closed-loop behavior of the HRI system for a given task. To obviate the requirement of the knowledge of the human model, integral reinforcement learning is used to solve the given LQR problem. Simulation results on an x - y table and a robot arm, and experimental implementation results on a PR2 robot confirm the suitability of the proposed method.

  12. Early Childhood Numeracy in a Multiage Setting

    Science.gov (United States)

    Wood, Karen; Frid, Sandra

    2005-01-01

    This research is a case study examining numeracy teaching and learning practices in an early childhood multiage setting with Pre-Primary to Year 2 children. Data were collected via running records, researcher reflection notes, and video and audio recordings. Video and audio transcripts were analysed using a mathematical discourse and social…

  13. Dynamic Sensor Tasking for Space Situational Awareness via Reinforcement Learning

    Science.gov (United States)

    Linares, R.; Furfaro, R.

    2016-09-01

    This paper studies the Sensor Management (SM) problem for optical Space Object (SO) tracking. The tasking problem is formulated as a Markov Decision Process (MDP) and solved using Reinforcement Learning (RL). The RL problem is solved using the actor-critic policy gradient approach. The actor provides a policy which is random over actions and given by a parametric probability density function (pdf). The critic evaluates the policy by calculating the estimated total reward or the value function for the problem. The parameters of the policy action pdf are optimized using gradients with respect to the reward function. Both the critic and the actor are modeled using deep neural networks (multi-layer neural networks). The policy neural network takes the current state as input and outputs probabilities for each possible action. This policy is random, and can be evaluated by sampling random actions using the probabilities determined by the policy neural network's outputs. The critic approximates the total reward using a neural network. The estimated total reward is used to approximate the gradient of the policy network with respect to the network parameters. This approach is used to find the non-myopic optimal policy for tasking optical sensors to estimate SO orbits. The reward function is based on reducing the uncertainty for the overall catalog to below a user specified uncertainty threshold. This work uses a 30 km total position error for the uncertainty threshold. This work provides the RL method with a negative reward as long as any SO has a total position error above the uncertainty threshold. This penalizes policies that take longer to achieve the desired accuracy. A positive reward is provided when all SOs are below the catalog uncertainty threshold. An optimal policy is sought that takes actions to achieve the desired catalog uncertainty in minimum time. This work trains the policy in simulation by letting it task a single sensor to "learn" from its performance

  14. A reward optimization method based on action subrewards in hierarchical reinforcement learning.

    Science.gov (United States)

    Fu, Yuchen; Liu, Quan; Ling, Xionghong; Cui, Zhiming

    2014-01-01

    Reinforcement learning (RL) is one kind of interactive learning methods. Its main characteristics are "trial and error" and "related reward." A hierarchical reinforcement learning method based on action subrewards is proposed to solve the problem of "curse of dimensionality," which means that the states space will grow exponentially in the number of features and low convergence speed. The method can reduce state spaces greatly and choose actions with favorable purpose and efficiency so as to optimize reward function and enhance convergence speed. Apply it to the online learning in Tetris game, and the experiment result shows that the convergence speed of this algorithm can be enhanced evidently based on the new method which combines hierarchical reinforcement learning algorithm and action subrewards. The "curse of dimensionality" problem is also solved to a certain extent with hierarchical method. All the performance with different parameters is compared and analyzed as well.

  15. Cognitive Medical Multiagent Systems

    OpenAIRE

    Barna Iantovics

    2010-01-01

    The development of efficient and flexible agent-based medical diagnosis systems represents a recent research direction. Medical multiagent systems may improve the efficiency of traditionally developed medical computational systems, like the medical expert systems. In our previous researches, a novel cooperative medical diagnosis multiagent system called CMDS (Contract Net Based Medical Diagnosis System) was proposed. CMDS system can solve flexibly a large variety of medical diagnosis problems...

  16. Adolescent-specific patterns of behavior and neural activity during social reinforcement learning.

    Science.gov (United States)

    Jones, Rebecca M; Somerville, Leah H; Li, Jian; Ruberry, Erika J; Powers, Alisa; Mehta, Natasha; Dyke, Jonathan; Casey, B J

    2014-06-01

    Humans are sophisticated social beings. Social cues from others are exceptionally salient, particularly during adolescence. Understanding how adolescents interpret and learn from variable social signals can provide insight into the observed shift in social sensitivity during this period. The present study tested 120 participants between the ages of 8 and 25 years on a social reinforcement learning task where the probability of receiving positive social feedback was parametrically manipulated. Seventy-eight of these participants completed the task during fMRI scanning. Modeling trial-by-trial learning, children and adults showed higher positive learning rates than did adolescents, suggesting that adolescents demonstrated less differentiation in their reaction times for peers who provided more positive feedback. Forming expectations about receiving positive social reinforcement correlated with neural activity within the medial prefrontal cortex and ventral striatum across age. Adolescents, unlike children and adults, showed greater insular activity during positive prediction error learning and increased activity in the supplementary motor cortex and the putamen when receiving positive social feedback regardless of the expected outcome, suggesting that peer approval may motivate adolescents toward action. While different amounts of positive social reinforcement enhanced learning in children and adults, all positive social reinforcement equally motivated adolescents. Together, these findings indicate that sensitivity to peer approval during adolescence goes beyond simple reinforcement theory accounts and suggest possible explanations for how peers may motivate adolescent behavior.

  17. Temporal Memory Reinforcement Learning for the Autonomous Micro-mobile Robot Based-behavior

    Institute of Scientific and Technical Information of China (English)

    Yang Yujun(杨玉君); Cheng Junshi; Chen Jiapin; Li Xiaohai

    2004-01-01

    This paper presents temporal memory reinforcement learning for the autonomous micro-mobile robot based-behavior. Human being has a memory oblivion process, i.e. the earlier to memorize, the earlier to forget, only the repeated thing can be remembered firmly. Enlightening forms this, and the robot need not memorize all the past states, at the same time economizes the EMS memory space, which is not enough in the MPU of our AMRobot. The proposed algorithm is an extension of the Q-learning, which is an incremental reinforcement learning method. The results of simulation have shown that the algorithm is valid.

  18. Video Demo: Deep Reinforcement Learning for Coordination in Traffic Light Control

    NARCIS (Netherlands)

    van der Pol, E.; Oliehoek, F.A.; Bosse, T.; Bredeweg, B.

    2016-01-01

    This video demonstration contrasts two approaches to coordination in traffic light control using reinforcement learning: earlier work, based on a deconstruction of the state space into a linear combination of vehicle states, and our own approach based on the Deep Q-learning algorithm.

  19. Pragmatically Framed Cross-Situational Noun Learning Using Computational Reinforcement Models.

    Science.gov (United States)

    Najnin, Shamima; Banerjee, Bonny

    2018-01-01

    Cross-situational learning and social pragmatic theories are prominent mechanisms for learning word meanings (i.e., word-object pairs). In this paper, the role of reinforcement is investigated for early word-learning by an artificial agent. When exposed to a group of speakers, the agent comes to understand an initial set of vocabulary items belonging to the language used by the group. Both cross-situational learning and social pragmatic theory are taken into account. As social cues, joint attention and prosodic cues in caregiver's speech are considered. During agent-caregiver interaction, the agent selects a word from the caregiver's utterance and learns the relations between that word and the objects in its visual environment. The "novel words to novel objects" language-specific constraint is assumed for computing rewards. The models are learned by maximizing the expected reward using reinforcement learning algorithms [i.e., table-based algorithms: Q-learning, SARSA, SARSA-λ, and neural network-based algorithms: Q-learning for neural network (Q-NN), neural-fitted Q-network (NFQ), and deep Q-network (DQN)]. Neural network-based reinforcement learning models are chosen over table-based models for better generalization and quicker convergence. Simulations are carried out using mother-infant interaction CHILDES dataset for learning word-object pairings. Reinforcement is modeled in two cross-situational learning cases: (1) with joint attention (Attentional models), and (2) with joint attention and prosodic cues (Attentional-prosodic models). Attentional-prosodic models manifest superior performance to Attentional ones for the task of word-learning. The Attentional-prosodic DQN outperforms existing word-learning models for the same task.

  20. The drift diffusion model as the choice rule in reinforcement learning.

    Science.gov (United States)

    Pedersen, Mads Lund; Frank, Michael J; Biele, Guido

    2017-08-01

    Current reinforcement-learning models often assume simplified decision processes that do not fully reflect the dynamic complexities of choice processes. Conversely, sequential-sampling models of decision making account for both choice accuracy and response time, but assume that decisions are based on static decision values. To combine these two computational models of decision making and learning, we implemented reinforcement-learning models in which the drift diffusion model describes the choice process, thereby capturing both within- and across-trial dynamics. To exemplify the utility of this approach, we quantitatively fit data from a common reinforcement-learning paradigm using hierarchical Bayesian parameter estimation, and compared model variants to determine whether they could capture the effects of stimulant medication in adult patients with attention-deficit hyperactivity disorder (ADHD). The model with the best relative fit provided a good description of the learning process, choices, and response times. A parameter recovery experiment showed that the hierarchical Bayesian modeling approach enabled accurate estimation of the model parameters. The model approach described here, using simultaneous estimation of reinforcement-learning and drift diffusion model parameters, shows promise for revealing new insights into the cognitive and neural mechanisms of learning and decision making, as well as the alteration of such processes in clinical groups.

  1. EFFICIENT SPECTRUM UTILIZATION IN COGNITIVE RADIO THROUGH REINFORCEMENT LEARNING

    Directory of Open Access Journals (Sweden)

    Dhananjay Kumar

    2013-09-01

    Full Text Available Machine learning schemes can be employed in cognitive radio systems to intelligently locate the spectrum holes with some knowledge about the operating environment. In this paper, we formulate a variation of Actor Critic Learning algorithm known as Continuous Actor Critic Learning Automaton (CACLA and compare this scheme with Actor Critic Learning scheme and existing Q–learning scheme. Simulation results show that our CACLA scheme has lesser execution time and achieves higher throughput compared to other two schemes.

  2. Adversarial Reinforcement Learning in a Cyber Security Simulation}

    NARCIS (Netherlands)

    Elderman, Richard; Pater, Leon; Thie, Albert; Drugan, Madalina; Wiering, Marco

    2017-01-01

    This paper focuses on cyber-security simulations in networks modeled as a Markov game with incomplete information and stochastic elements. The resulting game is an adversarial sequential decision making problem played with two agents, the attacker and defender. The two agents pit one reinforcement

  3. Interactions in multiagent systems fairness, social optimality and individual rationality

    CERN Document Server

    Hao, Jianye

    2016-01-01

    This book mainly aims at solving the problems in both cooperative and competitive multi-agent systems (MASs), exploring aspects such as how agents can effectively learn to achieve the shared optimal solution based on their local information and how they can learn to increase their individual utility by exploiting the weakness of their opponents. The book describes fundamental and advanced techniques of how multi-agent systems can be engineered towards the goal of ensuring fairness, social optimality, and individual rationality; a wide range of further relevant topics are also covered both theoretically and experimentally. The book will be beneficial to researchers in the fields of multi-agent systems, game theory and artificial intelligence in general, as well as practitioners developing practical multi-agent systems.

  4. Decision Making in Reinforcement Learning Using a Modified Learning Space Based on the Importance of Sensors

    Directory of Open Access Journals (Sweden)

    Yasutaka Kishima

    2013-01-01

    Full Text Available Many studies have been conducted on the application of reinforcement learning (RL to robots. A robot which is made for general purpose has redundant sensors or actuators because it is difficult to assume an environment that the robot will face and a task that the robot must execute. In this case, -space on RL contains redundancy so that the robot must take much time to learn a given task. In this study, we focus on the importance of sensors with regard to a robot’s performance of a particular task. The sensors that are applicable to a task differ according to the task. By using the importance of the sensors, we try to adjust the state number of the sensors and to reduce the size of -space. In this paper, we define the measure of importance of a sensor for a task with the correlation between the value of each sensor and reward. A robot calculates the importance of the sensors and makes the size of -space smaller. We propose the method which reduces learning space and construct the learning system by putting it in RL. In this paper, we confirm the effectiveness of our proposed system with an experimental robot.

  5. Neural correlates of reinforcement learning and social preferences in competitive bidding.

    Science.gov (United States)

    van den Bos, Wouter; Talwar, Arjun; McClure, Samuel M

    2013-01-30

    In competitive social environments, people often deviate from what rational choice theory prescribes, resulting in losses or suboptimal monetary gains. We investigate how competition affects learning and decision-making in a common value auction task. During the experiment, groups of five human participants were simultaneously scanned using MRI while playing the auction task. We first demonstrate that bidding is well characterized by reinforcement learning with biased reward representations dependent on social preferences. Indicative of reinforcement learning, we found that estimated trial-by-trial prediction errors correlated with activity in the striatum and ventromedial prefrontal cortex. Additionally, we found that individual differences in social preferences were related to activity in the temporal-parietal junction and anterior insula. Connectivity analyses suggest that monetary and social value signals are integrated in the ventromedial prefrontal cortex and striatum. Based on these results, we argue for a novel mechanistic account for the integration of reinforcement history and social preferences in competitive decision-making.

  6. A Robust Cooperated Control Method with Reinforcement Learning and Adaptive H∞ Control

    Science.gov (United States)

    Obayashi, Masanao; Uchiyama, Shogo; Kuremoto, Takashi; Kobayashi, Kunikazu

    This study proposes a robust cooperated control method combining reinforcement learning with robust control to control the system. A remarkable characteristic of the reinforcement learning is that it doesn't require model formula, however, it doesn't guarantee the stability of the system. On the other hand, robust control system guarantees stability and robustness, however, it requires model formula. We employ both the actor-critic method which is a kind of reinforcement learning with minimal amount of computation to control continuous valued actions and the traditional robust control, that is, H∞ control. The proposed system was compared method with the conventional control method, that is, the actor-critic only used, through the computer simulation of controlling the angle and the position of a crane system, and the simulation result showed the effectiveness of the proposed method.

  7. Learning Similar Actions by Reinforcement or Sensory-Prediction Errors Rely on Distinct Physiological Mechanisms.

    Science.gov (United States)

    Uehara, Shintaro; Mawase, Firas; Celnik, Pablo

    2017-09-14

    Humans can acquire knowledge of new motor behavior via different forms of learning. The two forms most commonly studied have been the development of internal models based on sensory-prediction errors (error-based learning) and success-based feedback (reinforcement learning). Human behavioral studies suggest these are distinct learning processes, though the neurophysiological mechanisms that are involved have not been characterized. Here, we evaluated physiological markers from the cerebellum and the primary motor cortex (M1) using noninvasive brain stimulations while healthy participants trained finger-reaching tasks. We manipulated the extent to which subjects rely on error-based or reinforcement by providing either vector or binary feedback about task performance. Our results demonstrated a double dissociation where learning the task mainly via error-based mechanisms leads to cerebellar plasticity modifications but not long-term potentiation (LTP)-like plasticity changes in M1; while learning a similar action via reinforcement mechanisms elicited M1 LTP-like plasticity but not cerebellar plasticity changes. Our findings indicate that learning complex motor behavior is mediated by the interplay of different forms of learning, weighing distinct neural mechanisms in M1 and the cerebellum. Our study provides insights for designing effective interventions to enhance human motor learning. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

  8. Self-learning fuzzy logic controllers based on reinforcement

    International Nuclear Information System (INIS)

    Wang, Z.; Shao, S.; Ding, J.

    1996-01-01

    This paper proposes a new method for learning and tuning Fuzzy Logic Controllers. The self-learning scheme in this paper is composed of Bucket-Brigade and Genetic Algorithm. The proposed method is tested on the cart-pole system. Simulation results show that our approach has good learning and control performance

  9. Experiments with Online Reinforcement Learning in Real-Time Strategy Games

    DEFF Research Database (Denmark)

    Toftgaard Andersen, Kresten; Zeng, Yifeng; Dahl Christensen, Dennis

    2009-01-01

    Real-time strategy (RTS) games provide a challenging platform to implement online reinforcement learning (RL) techniques in a real application. Computer, as one game player, monitors opponents' (human or other computers) strategies and then updates its own policy using RL methods. In this article......, we first examine the suitability of applying the online RL in various computer games. Reinforcement learning application depends on both RL complexity and the game features. We then propose a multi-layer framework for implementing online RL in an RTS game. The framework significantly reduces RL...... the effectiveness of our proposed framework and shed light on relevant issues in using online RL in RTS games....

  10. A Model to Explain the Emergence of Reward Expectancy neurons using Reinforcement Learning and Neural Network

    OpenAIRE

    Shinya, Ishii; Munetaka, Shidara; Katsunari, Shibata

    2006-01-01

    In an experiment of multi-trial task to obtain a reward, reward expectancy neurons,###which responded only in the non-reward trials that are necessary to advance###toward the reward, have been observed in the anterior cingulate cortex of monkeys.###In this paper, to explain the emergence of the reward expectancy neuron in###terms of reinforcement learning theory, a model that consists of a recurrent neural###network trained based on reinforcement learning is proposed. The analysis of the###hi...

  11. Neural prediction errors reveal a risk-sensitive reinforcement-learning process in the human brain.

    Science.gov (United States)

    Niv, Yael; Edlund, Jeffrey A; Dayan, Peter; O'Doherty, John P

    2012-01-11

    Humans and animals are exquisitely, though idiosyncratically, sensitive to risk or variance in the outcomes of their actions. Economic, psychological, and neural aspects of this are well studied when information about risk is provided explicitly. However, we must normally learn about outcomes from experience, through trial and error. Traditional models of such reinforcement learning focus on learning about the mean reward value of cues and ignore higher order moments such as variance. We used fMRI to test whether the neural correlates of human reinforcement learning are sensitive to experienced risk. Our analysis focused on anatomically delineated regions of a priori interest in the nucleus accumbens, where blood oxygenation level-dependent (BOLD) signals have been suggested as correlating with quantities derived from reinforcement learning. We first provide unbiased evidence that the raw BOLD signal in these regions corresponds closely to a reward prediction error. We then derive from this signal the learned values of cues that predict rewards of equal mean but different variance and show that these values are indeed modulated by experienced risk. Moreover, a close neurometric-psychometric coupling exists between the fluctuations of the experience-based evaluations of risky options that we measured neurally and the fluctuations in behavioral risk aversion. This suggests that risk sensitivity is integral to human learning, illuminating economic models of choice, neuroscientific models of affective learning, and the workings of the underlying neural mechanisms.

  12. Cognitive Medical Multiagent Systems

    Directory of Open Access Journals (Sweden)

    Barna Iantovics

    2010-01-01

    Full Text Available The development of efficient and flexible agent-based medical diagnosis systems represents a recent research direction. Medical multiagent systems may improve the efficiency of traditionally developed medical computational systems, like the medical expert systems. In our previous researches, a novel cooperative medical diagnosis multiagent system called CMDS (Contract Net Based Medical Diagnosis System was proposed. CMDS system can solve flexibly a large variety of medical diagnosis problems. This paper analyses the increased intelligence of the CMDS system, which motivates its use for different medical problem’s solving.

  13. Semi-Cooperative Learning in Smart Grid Agents

    Science.gov (United States)

    2013-12-01

    this PhD program , but watching you grow has only made me realize how much more awesome human learning is. You have been a source of profound joy and...which should alleviate concern for scala - bility along this dimension. • Learning the negotiation model: Figure 6.23 shows single-episode results that...for Semi-cooperative Multi-agent Coordination. In IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning . [Prendergast, 1999

  14. Cardiac Concomitants of Feedback and Prediction Error Processing in Reinforcement Learning

    Science.gov (United States)

    Kastner, Lucas; Kube, Jana; Villringer, Arno; Neumann, Jane

    2017-01-01

    Successful learning hinges on the evaluation of positive and negative feedback. We assessed differential learning from reward and punishment in a monetary reinforcement learning paradigm, together with cardiac concomitants of positive and negative feedback processing. On the behavioral level, learning from reward resulted in more advantageous behavior than learning from punishment, suggesting a differential impact of reward and punishment on successful feedback-based learning. On the autonomic level, learning and feedback processing were closely mirrored by phasic cardiac responses on a trial-by-trial basis: (1) Negative feedback was accompanied by faster and prolonged heart rate deceleration compared to positive feedback. (2) Cardiac responses shifted from feedback presentation at the beginning of learning to stimulus presentation later on. (3) Most importantly, the strength of phasic cardiac responses to the presentation of feedback correlated with the strength of prediction error signals that alert the learner to the necessity for behavioral adaptation. Considering participants' weight status and gender revealed obesity-related deficits in learning to avoid negative consequences and less consistent behavioral adaptation in women compared to men. In sum, our results provide strong new evidence for the notion that during learning phasic cardiac responses reflect an internal value and feedback monitoring system that is sensitive to the violation of performance-based expectations. Moreover, inter-individual differences in weight status and gender may affect both behavioral and autonomic responses in reinforcement-based learning. PMID:29163004

  15. Cardiac Concomitants of Feedback and Prediction Error Processing in Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Lucas Kastner

    2017-10-01

    Full Text Available Successful learning hinges on the evaluation of positive and negative feedback. We assessed differential learning from reward and punishment in a monetary reinforcement learning paradigm, together with cardiac concomitants of positive and negative feedback processing. On the behavioral level, learning from reward resulted in more advantageous behavior than learning from punishment, suggesting a differential impact of reward and punishment on successful feedback-based learning. On the autonomic level, learning and feedback processing were closely mirrored by phasic cardiac responses on a trial-by-trial basis: (1 Negative feedback was accompanied by faster and prolonged heart rate deceleration compared to positive feedback. (2 Cardiac responses shifted from feedback presentation at the beginning of learning to stimulus presentation later on. (3 Most importantly, the strength of phasic cardiac responses to the presentation of feedback correlated with the strength of prediction error signals that alert the learner to the necessity for behavioral adaptation. Considering participants' weight status and gender revealed obesity-related deficits in learning to avoid negative consequences and less consistent behavioral adaptation in women compared to men. In sum, our results provide strong new evidence for the notion that during learning phasic cardiac responses reflect an internal value and feedback monitoring system that is sensitive to the violation of performance-based expectations. Moreover, inter-individual differences in weight status and gender may affect both behavioral and autonomic responses in reinforcement-based learning.

  16. Safe robot execution in model-based reinforcement learning

    OpenAIRE

    Martínez Martínez, David; Alenyà Ribas, Guillem; Torras, Carme

    2015-01-01

    Task learning in robotics requires repeatedly executing the same actions in different states to learn the model of the task. However, in real-world domains, there are usually sequences of actions that, if executed, may produce unrecoverable errors (e.g. breaking an object). Robots should avoid repeating such errors when learning, and thus explore the state space in a more intelligent way. This requires identifying dangerous action effects to avoid including such actions in the generated plans...

  17. Reinforcement function design and bias for efficient learning in mobile robots

    International Nuclear Information System (INIS)

    Touzet, C.; Santos, J.M.

    1998-01-01

    The main paradigm in sub-symbolic learning robot domain is the reinforcement learning method. Various techniques have been developed to deal with the memorization/generalization problem, demonstrating the superior ability of artificial neural network implementations. In this paper, the authors address the issue of designing the reinforcement so as to optimize the exploration part of the learning. They also present and summarize works relative to the use of bias intended to achieve the effective synthesis of the desired behavior. Demonstrative experiments involving a self-organizing map implementation of the Q-learning and real mobile robots (Nomad 200 and Khepera) in a task of obstacle avoidance behavior synthesis are described. 3 figs., 5 tabs

  18. Critical factors in the empirical performance of temporal difference and evolutionary methods for reinforcement learning

    NARCIS (Netherlands)

    Whiteson, S.; Taylor, M.E.; Stone, P.

    2010-01-01

    Temporal difference and evolutionary methods are two of the most common approaches to solving reinforcement learning problems. However, there is little consensus on their relative merits and there have been few empirical studies that directly compare their performance. This article aims to address

  19. Energy Management Strategy for a Hybrid Electric Vehicle Based on Deep Reinforcement Learning

    OpenAIRE

    Yue Hu; Weimin Li; Kun Xu; Taimoor Zahid; Feiyan Qin; Chenming Li

    2018-01-01

    An energy management strategy (EMS) is important for hybrid electric vehicles (HEVs) since it plays a decisive role on the performance of the vehicle. However, the variation of future driving conditions deeply influences the effectiveness of the EMS. Most existing EMS methods simply follow predefined rules that are not adaptive to different driving conditions online. Therefore, it is useful that the EMS can learn from the environment or driving cycle. In this paper, a deep reinforcement learn...

  20. Adolescent-specific patterns of behavior and neural activity during social reinforcement learning

    OpenAIRE

    Jones, Rebecca M.; Somerville, Leah H.; Li, Jian; Ruberry, Erika J.; Powers, Alisa; Mehta, Natasha; Dyke, Jonathan; Casey, BJ

    2014-01-01

    Humans are sophisticated social beings. Social cues from others are exceptionally salient, particularly during adolescence. Understanding how adolescents interpret and learn from variable social signals can provide insight into the observed shift in social sensitivity during this period. The current study tested 120 participants between the ages of 8 and 25 years on a social reinforcement learning task where the probability of receiving positive social feedback was parametrically manipulated....

  1. Active-learning strategies: the use of a game to reinforce learning in nursing education. A case study.

    Science.gov (United States)

    Boctor, Lisa

    2013-03-01

    The majority of nursing students are kinesthetic learners, preferring a hands-on, active approach to education. Research shows that active-learning strategies can increase student learning and satisfaction. This study looks at the use of one active-learning strategy, a Jeopardy-style game, 'Nursopardy', to reinforce Fundamentals of Nursing material, aiding in students' preparation for a standardized final exam. The game was created keeping students varied learning styles and the NCLEX blueprint in mind. The blueprint was used to create 5 categories, with 26 total questions. Student survey results, using a five-point Likert scale showed that they did find this learning method enjoyable and beneficial to learning. More research is recommended regarding learning outcomes, when using active-learning strategies, such as games. Copyright © 2012 Elsevier Ltd. All rights reserved.

  2. Gaze-contingent reinforcement learning reveals incentive value of social signals in young children and adults.

    Science.gov (United States)

    Vernetti, Angélina; Smith, Tim J; Senju, Atsushi

    2017-03-15

    While numerous studies have demonstrated that infants and adults preferentially orient to social stimuli, it remains unclear as to what drives such preferential orienting. It has been suggested that the learned association between social cues and subsequent reward delivery might shape such social orienting. Using a novel, spontaneous indication of reinforcement learning (with the use of a gaze contingent reward-learning task), we investigated whether children and adults' orienting towards social and non-social visual cues can be elicited by the association between participants' visual attention and a rewarding outcome. Critically, we assessed whether the engaging nature of the social cues influences the process of reinforcement learning. Both children and adults learned to orient more often to the visual cues associated with reward delivery, demonstrating that cue-reward association reinforced visual orienting. More importantly, when the reward-predictive cue was social and engaging, both children and adults learned the cue-reward association faster and more efficiently than when the reward-predictive cue was social but non-engaging. These new findings indicate that social engaging cues have a positive incentive value. This could possibly be because they usually coincide with positive outcomes in real life, which could partly drive the development of social orienting. © 2017 The Authors.

  3. High and low temperatures have unequal reinforcing properties in Drosophila spatial learning.

    Science.gov (United States)

    Zars, Melissa; Zars, Troy

    2006-07-01

    Small insects regulate their body temperature solely through behavior. Thus, sensing environmental temperature and implementing an appropriate behavioral strategy can be critical for survival. The fly Drosophila melanogaster prefers 24 degrees C, avoiding higher and lower temperatures when tested on a temperature gradient. Furthermore, temperatures above 24 degrees C have negative reinforcing properties. In contrast, we found that flies have a preference in operant learning experiments for a low-temperature-associated position rather than the 24 degrees C alternative in the heat-box. Two additional differences between high- and low-temperature reinforcement, i.e., temperatures above and below 24 degrees C, were found. Temperatures equally above and below 24 degrees C did not reinforce equally and only high temperatures supported increased memory performance with reversal conditioning. Finally, low- and high-temperature reinforced memories are similarly sensitive to two genetic mutations. Together these results indicate the qualitative meaning of temperatures below 24 degrees C depends on the dynamics of the temperatures encountered and that the reinforcing effects of these temperatures depend on at least some common genetic components. Conceptualizing these results using the Wolf-Heisenberg model of operant conditioning, we propose the maximum difference in experienced temperatures determines the magnitude of the reinforcement input to a conditioning circuit.

  4. Cerebellar and prefrontal cortex contributions to adaptation, strategies, and reinforcement learning.

    Science.gov (United States)

    Taylor, Jordan A; Ivry, Richard B

    2014-01-01

    Traditionally, motor learning has been studied as an implicit learning process, one in which movement errors are used to improve performance in a continuous, gradual manner. The cerebellum figures prominently in this literature given well-established ideas about the role of this system in error-based learning and the production of automatized skills. Recent developments have brought into focus the relevance of multiple learning mechanisms for sensorimotor learning. These include processes involving repetition, reinforcement learning, and strategy utilization. We examine these developments, considering their implications for understanding cerebellar function and how this structure interacts with other neural systems to support motor learning. Converging lines of evidence from behavioral, computational, and neuropsychological studies suggest a fundamental distinction between processes that use error information to improve action execution or action selection. While the cerebellum is clearly linked to the former, its role in the latter remains an open question. © 2014 Elsevier B.V. All rights reserved.

  5. From scorecard to social learning: a reflective coassessment approach for promoting multiagency cooperation in natural resource management

    CSIR Research Space (South Africa)

    Roux, DJ

    2011-01-01

    Full Text Available resource management are usually confined to single organizations. This paper describes a social learning approach which acknowledges cooperation as an essential precondition for effective management and that encourages reflective coassessment of cooperative...

  6. Confirmation bias in human reinforcement learning: Evidence from counterfactual feedback processing

    Science.gov (United States)

    Lefebvre, Germain; Blakemore, Sarah-Jayne

    2017-01-01

    Previous studies suggest that factual learning, that is, learning from obtained outcomes, is biased, such that participants preferentially take into account positive, as compared to negative, prediction errors. However, whether or not the prediction error valence also affects counterfactual learning, that is, learning from forgone outcomes, is unknown. To address this question, we analysed the performance of two groups of participants on reinforcement learning tasks using a computational model that was adapted to test if prediction error valence influences learning. We carried out two experiments: in the factual learning experiment, participants learned from partial feedback (i.e., the outcome of the chosen option only); in the counterfactual learning experiment, participants learned from complete feedback information (i.e., the outcomes of both the chosen and unchosen option were displayed). In the factual learning experiment, we replicated previous findings of a valence-induced bias, whereby participants learned preferentially from positive, relative to negative, prediction errors. In contrast, for counterfactual learning, we found the opposite valence-induced bias: negative prediction errors were preferentially taken into account, relative to positive ones. When considering valence-induced bias in the context of both factual and counterfactual learning, it appears that people tend to preferentially take into account information that confirms their current choice. PMID:28800597

  7. Confirmation bias in human reinforcement learning: Evidence from counterfactual feedback processing.

    Science.gov (United States)

    Palminteri, Stefano; Lefebvre, Germain; Kilford, Emma J; Blakemore, Sarah-Jayne

    2017-08-01

    Previous studies suggest that factual learning, that is, learning from obtained outcomes, is biased, such that participants preferentially take into account positive, as compared to negative, prediction errors. However, whether or not the prediction error valence also affects counterfactual learning, that is, learning from forgone outcomes, is unknown. To address this question, we analysed the performance of two groups of participants on reinforcement learning tasks using a computational model that was adapted to test if prediction error valence influences learning. We carried out two experiments: in the factual learning experiment, participants learned from partial feedback (i.e., the outcome of the chosen option only); in the counterfactual learning experiment, participants learned from complete feedback information (i.e., the outcomes of both the chosen and unchosen option were displayed). In the factual learning experiment, we replicated previous findings of a valence-induced bias, whereby participants learned preferentially from positive, relative to negative, prediction errors. In contrast, for counterfactual learning, we found the opposite valence-induced bias: negative prediction errors were preferentially taken into account, relative to positive ones. When considering valence-induced bias in the context of both factual and counterfactual learning, it appears that people tend to preferentially take into account information that confirms their current choice.

  8. Frontostriatal development and probabilistic reinforcement learning during adolescence.

    Science.gov (United States)

    DePasque, Samantha; Galván, Adriana

    2017-09-01

    Adolescence has traditionally been viewed as a period of vulnerability to increased risk-taking and adverse outcomes, which have been linked to neurobiological maturation of the frontostriatal reward system. However, growing research on the role of developmental changes in the adolescent frontostriatal system in facilitating learning will provide a more nuanced view of adolescence. In this review, we discuss the implications of existing research on this topic for learning during adolescence, and suggest that the very neural changes that render adolescents vulnerable to social pressure and risky decision making may also stand to play a role in scaffolding the ability to learn from rewards and from performance-related feedback. Copyright © 2017 Elsevier Inc. All rights reserved.

  9. Reinforcement Learning for Constrained Energy Trading Games With Incomplete Information.

    Science.gov (United States)

    Wang, Huiwei; Huang, Tingwen; Liao, Xiaofeng; Abu-Rub, Haitham; Chen, Guo

    2017-10-01

    This paper considers the problem of designing adaptive learning algorithms to seek the Nash equilibrium (NE) of the constrained energy trading game among individually strategic players with incomplete information. In this game, each player uses the learning automaton scheme to generate the action probability distribution based on his/her private information for maximizing his own averaged utility. It is shown that if one of admissible mixed-strategies converges to the NE with probability one, then the averaged utility and trading quantity almost surely converge to their expected ones, respectively. For the given discontinuous pricing function, the utility function has already been proved to be upper semicontinuous and payoff secure which guarantee the existence of the mixed-strategy NE. By the strict diagonal concavity of the regularized Lagrange function, the uniqueness of NE is also guaranteed. Finally, an adaptive learning algorithm is provided to generate the strategy probability distribution for seeking the mixed-strategy NE.

  10. Bi-directional effect of increasing doses of baclofen on reinforcement learning

    Directory of Open Access Journals (Sweden)

    Jean eTerrier

    2011-07-01

    Full Text Available In rodents as well as in humans, efficient reinforcement learning depends on dopamine (DA released from ventral tegmental area (VTA neurons. It has been shown that in brain slices of mice, GABAB-receptor agonists at low concentrations increase the firing frequency of VTA-DA neurons, while high concentrations reduce the firing frequency. It remains however elusive whether baclofen can modulate reinforcement learning. Here, in a double blind study in 34 healthy human volunteers, we tested the effects of a low and a high concentration of oral baclofen in a gambling task associated with monetary reward. A low (20 mg dose of baclofen increased the efficiency of reward-associated learning but had no effect on the avoidance of monetary loss. A high (50 mg dose of baclofen on the other hand did not affect the learning curve. At the end of the task, subjects who received 20 mg baclofen p.o. were more accurate in choosing the symbol linked to the highest probability of earning money compared to the control group (89.55±1.39% vs 81.07±1.55%, p=0.002. Our results support a model where baclofen, at low concentrations, causes a disinhibition of DA neurons, increases DA levels and thus facilitates reinforcement learning.

  11. Spared internal but impaired external reward prediction error signals in major depressive disorder during reinforcement learning.

    Science.gov (United States)

    Bakic, Jasmina; Pourtois, Gilles; Jepma, Marieke; Duprat, Romain; De Raedt, Rudi; Baeken, Chris

    2017-01-01

    Major depressive disorder (MDD) creates debilitating effects on a wide range of cognitive functions, including reinforcement learning (RL). In this study, we sought to assess whether reward processing as such, or alternatively the complex interplay between motivation and reward might potentially account for the abnormal reward-based learning in MDD. A total of 35 treatment resistant MDD patients and 44 age matched healthy controls (HCs) performed a standard probabilistic learning task. RL was titrated using behavioral, computational modeling and event-related brain potentials (ERPs) data. MDD patients showed comparable learning rate compared to HCs. However, they showed decreased lose-shift responses as well as blunted subjective evaluations of the reinforcers used during the task, relative to HCs. Moreover, MDD patients showed normal internal (at the level of error-related negativity, ERN) but abnormal external (at the level of feedback-related negativity, FRN) reward prediction error (RPE) signals during RL, selectively when additional efforts had to be made to establish learning. Collectively, these results lend support to the assumption that MDD does not impair reward processing per se during RL. Instead, it seems to alter the processing of the emotional value of (external) reinforcers during RL, when additional intrinsic motivational processes have to be engaged. © 2016 Wiley Periodicals, Inc.

  12. DYNAMIC AND INCREMENTAL EXPLORATION STRATEGY IN FUSION ADAPTIVE RESONANCE THEORY FOR ONLINE REINFORCEMENT LEARNING

    Directory of Open Access Journals (Sweden)

    Budhitama Subagdja

    2016-06-01

    Full Text Available One of the fundamental challenges in reinforcement learning is to setup a proper balance between exploration and exploitation to obtain the maximum cummulative reward in the long run. Most protocols for exploration bound the overall values to a convergent level of performance. If new knowledge is inserted or the environment is suddenly changed, the issue becomes more intricate as the exploration must compromise the pre-existing knowledge. This paper presents a type of multi-channel adaptive resonance theory (ART neural network model called fusion ART which serves as a fuzzy approximator for reinforcement learning with inherent features that can regulate the exploration strategy. This intrinsic regulation is driven by the condition of the knowledge learnt so far by the agent. The model offers a stable but incremental reinforcement learning that can involve prior rules as bootstrap knowledge for guiding the agent to select the right action. Experiments in obstacle avoidance and navigation tasks demonstrate that in the configuration of learning wherein the agent learns from scratch, the inherent exploration model in fusion ART model is comparable to the basic E-greedy policy. On the other hand, the model is demonstrated to deal with prior knowledge and strike a balance between exploration and exploitation.

  13. What Can Reinforcement Learning Teach Us About Non-Equilibrium Quantum Dynamics

    Science.gov (United States)

    Bukov, Marin; Day, Alexandre; Sels, Dries; Weinberg, Phillip; Polkovnikov, Anatoli; Mehta, Pankaj

    Equilibrium thermodynamics and statistical physics are the building blocks of modern science and technology. Yet, our understanding of thermodynamic processes away from equilibrium is largely missing. In this talk, I will reveal the potential of what artificial intelligence can teach us about the complex behaviour of non-equilibrium systems. Specifically, I will discuss the problem of finding optimal drive protocols to prepare a desired target state in quantum mechanical systems by applying ideas from Reinforcement Learning [one can think of Reinforcement Learning as the study of how an agent (e.g. a robot) can learn and perfect a given policy through interactions with an environment.]. The driving protocols learnt by our agent suggest that the non-equilibrium world features possibilities easily defying intuition based on equilibrium physics.

  14. Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning.

    Science.gov (United States)

    Pilarski, Patrick M; Dawson, Michael R; Degris, Thomas; Fahimi, Farbod; Carey, Jason P; Sutton, Richard S

    2011-01-01

    As a contribution toward the goal of adaptable, intelligent artificial limbs, this work introduces a continuous actor-critic reinforcement learning method for optimizing the control of multi-function myoelectric devices. Using a simulated upper-arm robotic prosthesis, we demonstrate how it is possible to derive successful limb controllers from myoelectric data using only a sparse human-delivered training signal, without requiring detailed knowledge about the task domain. This reinforcement-based machine learning framework is well suited for use by both patients and clinical staff, and may be easily adapted to different application domains and the needs of individual amputees. To our knowledge, this is the first my-oelectric control approach that facilitates the online learning of new amputee-specific motions based only on a one-dimensional (scalar) feedback signal provided by the user of the prosthesis. © 2011 IEEE

  15. TEXPLORE temporal difference reinforcement learning for robots and time-constrained domains

    CERN Document Server

    Hester, Todd

    2013-01-01

    This book presents and develops new reinforcement learning methods that enable fast and robust learning on robots in real-time. Robots have the potential to solve many problems in society, because of their ability to work in dangerous places doing necessary jobs that no one wants or is able to do. One barrier to their widespread deployment is that they are mainly limited to tasks where it is possible to hand-program behaviors for every situation that may be encountered. For robots to meet their potential, they need methods that enable them to learn and adapt to novel situations that they were not programmed for. Reinforcement learning (RL) is a paradigm for learning sequential decision making processes and could solve the problems of learning and adaptation on robots. This book identifies four key challenges that must be addressed for an RL algorithm to be practical for robotic control tasks. These RL for Robotics Challenges are: 1) it must learn in very few samples; 2) it must learn in domains with continuou...

  16. Instructional control of reinforcement learning: A behavioral and neurocomputational investigation

    NARCIS (Netherlands)

    Doll, B.B.; Jacobs, W.J.; Sanfey, A.G.; Frank, M.J.

    2009-01-01

    Humans learn how to behave directly through environmental experience and indirectly through rules and instructions. Behavior analytic research has shown that instructions can control behavior, even when such behavior leads to sub-optimal outcomes (Hayes, S (Ed) 1989. Rule-governed behavior:

  17. Engineering Multiagent Systems - Reflections

    DEFF Research Database (Denmark)

    Villadsen, Jørgen

    2012-01-01

    In the first part I look at a theater performance by artistic director Troels Christian Jakobsen as a multiagent system. It is designed as a self-organising critical system using a framework where within its borders but without a script there is real interaction between the elements of the perfor......In the first part I look at a theater performance by artistic director Troels Christian Jakobsen as a multiagent system. It is designed as a self-organising critical system using a framework where within its borders but without a script there is real interaction between the elements...... of the performance. In the second part I discuss the ideas behind my recent monograph on propositional attitudes and inconsistency tolerance. Natural language sentences are parsed using a categorial grammar and correctness of arguments are decided using a paraconsistent logic. In the third part I present...

  18. Autonomous Inter-Task Transfer in Reinforcement Learning Domains

    Science.gov (United States)

    2008-08-01

    Mountain Car. However, because the source task uses a car with a motor more than twice as powerful as in the 3D task, the tran- sition function learned in...powerful car motor or changing the surface friction of the hill • s: changing the range of the state variables • si: changing where the car starts...Aamodt and Enric Plaza. Case-based reasoning: Foundational issues, methodological variations, and system approaches, 1994. Mazda Ahmadi, Matthew E

  19. Stress Modulates Reinforcement Learning in Younger and Older Adults

    OpenAIRE

    Lighthall, Nichole R.; Gorlick, Marissa A.; Schoeke, Andrej; Frank, Michael J.; Mather, Mara

    2012-01-01

    Animal research and human neuroimaging studies indicate that stress increases dopamine levels in brain regions involved in reward processing and stress also appears to increase the attractiveness of addictive drugs. The current study tested the hypothesis that stress increases reward salience, leading to more effective learning about positive than negative outcomes in a probabilistic selection task. Changes to dopamine pathways with age raise the question of whether stress effects on incentiv...

  20. Dissociable neural representations of reinforcement and belief prediction errors underlie strategic learning.

    Science.gov (United States)

    Zhu, Lusha; Mathewson, Kyle E; Hsu, Ming

    2012-01-31

    Decision-making in the presence of other competitive intelligent agents is fundamental for social and economic behavior. Such decisions require agents to behave strategically, where in addition to learning about the rewards and punishments available in the environment, they also need to anticipate and respond to actions of others competing for the same rewards. However, whereas we know much about strategic learning at both theoretical and behavioral levels, we know relatively little about the underlying neural mechanisms. Here, we show using a multi-strategy competitive learning paradigm that strategic choices can be characterized by extending the reinforcement learning (RL) framework to incorporate agents' beliefs about the actions of their opponents. Furthermore, using this characterization to generate putative internal values, we used model-based functional magnetic resonance imaging to investigate neural computations underlying strategic learning. We found that the distinct notions of prediction errors derived from our computational model are processed in a partially overlapping but distinct set of brain regions. Specifically, we found that the RL prediction error was correlated with activity in the ventral striatum. In contrast, activity in the ventral striatum, as well as the rostral anterior cingulate (rACC), was correlated with a previously uncharacterized belief-based prediction error. Furthermore, activity in rACC reflected individual differences in degree of engagement in belief learning. These results suggest a model of strategic behavior where learning arises from interaction of dissociable reinforcement and belief-based inputs.

  1. Learning from demonstration: Teaching a myoelectric prosthesis with an intact limb via reinforcement learning.

    Science.gov (United States)

    Vasan, Gautham; Pilarski, Patrick M

    2017-07-01

    Prosthetic arms should restore and extend the capabilities of someone with an amputation. They should move naturally and be able to perform elegant, coordinated movements that approximate those of a biological arm. Despite these objectives, the control of modern-day prostheses is often nonintuitive and taxing. Existing devices and control approaches do not yet give users the ability to effect highly synergistic movements during their daily-life control of a prosthetic device. As a step towards improving the control of prosthetic arms and hands, we introduce an intuitive approach to training a prosthetic control system that helps a user achieve hard-to-engineer control behaviours. Specifically, we present an actor-critic reinforcement learning method that for the first time promises to allow someone with an amputation to use their non-amputated arm to teach their prosthetic arm how to move through a wide range of coordinated motions and grasp patterns. We evaluate our method during the myoelectric control of a multi-joint robot arm by non-amputee users, and demonstrate that by using our approach a user can train their arm to perform simultaneous gestures and movements in all three degrees of freedom in the robot's hand and wrist based only on information sampled from the robot and the user's above-elbow myoelectric signals. Our results indicate that this learning-from-demonstration paradigm may be well suited to use by both patients and clinicians with minimal technical knowledge, as it allows a user to personalize the control of his or her prosthesis without having to know the underlying mechanics of the prosthetic limb. These preliminary results also suggest that our approach may extend in a straightforward way to next-generation prostheses with precise finger and wrist control, such that these devices may someday allow users to perform fluid and intuitive movements like playing the piano, catching a ball, and comfortably shaking hands.

  2. Measuring reinforcement learning and motivation constructs in experimental animals: relevance to the negative symptoms of schizophrenia

    Science.gov (United States)

    Markou, Athina; Salamone, John D.; Bussey, Timothy; Mar, Adam; Brunner, Daniela; Gilmour, Gary; Balsam, Peter

    2013-01-01

    The present review article summarizes and expands upon the discussions that were initiated during a meeting of the Cognitive Neuroscience Treatment Research to Improve Cognition in Schizophrenia (CNTRICS; http://cntrics.ucdavis.edu). A major goal of the CNTRICS meeting was to identify experimental procedures and measures that can be used in laboratory animals to assess psychological constructs that are related to the psychopathology of schizophrenia. The issues discussed in this review reflect the deliberations of the Motivation Working Group of the CNTRICS meeting, which included most of the authors of this article as well as additional participants. After receiving task nominations from the general research community, this working group was asked to identify experimental procedures in laboratory animals that can assess aspects of reinforcement learning and motivation that may be relevant for research on the negative symptoms of schizophrenia, as well as other disorders characterized by deficits in reinforcement learning and motivation. The tasks described here that assess reinforcement learning are the Autoshaping Task, Probabilistic Reward Learning Tasks, and the Response Bias Probabilistic Reward Task. The tasks described here that assess motivation are Outcome Devaluation and Contingency Degradation Tasks and Effort-Based Tasks. In addition to describing such methods and procedures, the present article provides a working vocabulary for research and theory in this field, as well as an industry perspective about how such tasks may be used in drug discovery. It is hoped that this review can aid investigators who are conducting research in this complex area, promote translational studies by highlighting shared research goals and fostering a common vocabulary across basic and clinical fields, and facilitate the development of medications for the treatment of symptoms mediated by reinforcement learning and motivational deficits. PMID:23994273

  3. Measuring reinforcement learning and motivation constructs in experimental animals: relevance to the negative symptoms of schizophrenia.

    Science.gov (United States)

    Markou, Athina; Salamone, John D; Bussey, Timothy J; Mar, Adam C; Brunner, Daniela; Gilmour, Gary; Balsam, Peter

    2013-11-01

    The present review article summarizes and expands upon the discussions that were initiated during a meeting of the Cognitive Neuroscience Treatment Research to Improve Cognition in Schizophrenia (CNTRICS; http://cntrics.ucdavis.edu) meeting. A major goal of the CNTRICS meeting was to identify experimental procedures and measures that can be used in laboratory animals to assess psychological constructs that are related to the psychopathology of schizophrenia. The issues discussed in this review reflect the deliberations of the Motivation Working Group of the CNTRICS meeting, which included most of the authors of this article as well as additional participants. After receiving task nominations from the general research community, this working group was asked to identify experimental procedures in laboratory animals that can assess aspects of reinforcement learning and motivation that may be relevant for research on the negative symptoms of schizophrenia, as well as other disorders characterized by deficits in reinforcement learning and motivation. The tasks described here that assess reinforcement learning are the Autoshaping Task, Probabilistic Reward Learning Tasks, and the Response Bias Probabilistic Reward Task. The tasks described here that assess motivation are Outcome Devaluation and Contingency Degradation Tasks and Effort-Based Tasks. In addition to describing such methods and procedures, the present article provides a working vocabulary for research and theory in this field, as well as an industry perspective about how such tasks may be used in drug discovery. It is hoped that this review can aid investigators who are conducting research in this complex area, promote translational studies by highlighting shared research goals and fostering a common vocabulary across basic and clinical fields, and facilitate the development of medications for the treatment of symptoms mediated by reinforcement learning and motivational deficits. Copyright © 2013 Elsevier

  4. Reinforcement learning on slow features of high-dimensional input streams.

    Directory of Open Access Journals (Sweden)

    Robert Legenstein

    Full Text Available Humans and animals are able to learn complex behaviors based on a massive stream of sensory information from different modalities. Early animal studies have identified learning mechanisms that are based on reward and punishment such that animals tend to avoid actions that lead to punishment whereas rewarded actions are reinforced. However, most algorithms for reward-based learning are only applicable if the dimensionality of the state-space is sufficiently small or its structure is sufficiently simple. Therefore, the question arises how the problem of learning on high-dimensional data is solved in the brain. In this article, we propose a biologically plausible generic two-stage learning system that can directly be applied to raw high-dimensional input streams. The system is composed of a hierarchical slow feature analysis (SFA network for preprocessing and a simple neural network on top that is trained based on rewards. We demonstrate by computer simulations that this generic architecture is able to learn quite demanding reinforcement learning tasks on high-dimensional visual input streams in a time that is comparable to the time needed when an explicit highly informative low-dimensional state-space representation is given instead of the high-dimensional visual input. The learning speed of the proposed architecture in a task similar to the Morris water maze task is comparable to that found in experimental studies with rats. This study thus supports the hypothesis that slowness learning is one important unsupervised learning principle utilized in the brain to form efficient state representations for behavioral learning.

  5. Early childhood numeracy in a multiage setting

    Science.gov (United States)

    Wood, Karen; Frid, Sandra

    2005-10-01

    This research is a case study examining numeracy teaching and learning practices in an early childhood multiage setting with Pre-Primary to Year 2 children. Data were collected via running records, researcher reflection notes, and video and audio recordings. Video and audio transcripts were analysed using a mathematical discourse and social interactions coding system designed by MacMillan (1998), while the running records and reflection notes contributed to descriptions of the children's interactions with each other and with the teachers. Teachers used an `assisted performance' approach to instruction that supported problem solving and inquiry processes in mathematics activities, and this, combined with a child-centred pedagogy and specific values about community learning, created a learning environment designed to stimulate and foster learning. The mathematics discourse analysis showed a use of explanatory language in mathematics discourse, and this language supported scaffolding among children for new mathematics concepts. These and other interactions related to peer sharing, tutoring and regulation also emerged as key aspects of students' learning practices. However, the findings indicated that multiage grouping alone did not support learning. Rather, effective learning was dependent upon the teacher's capacities to develop productive discussion among children, as well as implement developmentally appropriate curricula that addressed the needs of the different children.

  6. A Review of the Relationship between Novelty, Intrinsic Motivation and Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Siddique Nazmul

    2017-11-01

    Full Text Available This paper presents a review on the tri-partite relationship between novelty, intrinsic motivation and reinforcement learning. The paper first presents a literature survey on novelty and the different computational models of novelty detection, with a specific focus on the features of stimuli that trigger a Hedonic value for generating a novelty signal. It then presents an overview of intrinsic motivation and investigations into different models with the aim of exploring deeper co-relationships between specific features of a novelty signal and its effect on intrinsic motivation in producing a reward function. Finally, it presents survey results on reinforcement learning, different models and their functional relationship with intrinsic motivation.

  7. Online Pedagogical Tutorial Tactics Optimization Using Genetic-Based Reinforcement Learning.

    Science.gov (United States)

    Lin, Hsuan-Ta; Lee, Po-Ming; Hsiao, Tzu-Chien

    2015-01-01

    Tutorial tactics are policies for an Intelligent Tutoring System (ITS) to decide the next action when there are multiple actions available. Recent research has demonstrated that when the learning contents were controlled so as to be the same, different tutorial tactics would make difference in students' learning gains. However, the Reinforcement Learning (RL) techniques that were used in previous studies to induce tutorial tactics are insufficient when encountering large problems and hence were used in offline manners. Therefore, we introduced a Genetic-Based Reinforcement Learning (GBML) approach to induce tutorial tactics in an online-learning manner without basing on any preexisting dataset. The introduced method can learn a set of rules from the environment in a manner similar to RL. It includes a genetic-based optimizer for rule discovery task by generating new rules from the old ones. This increases the scalability of a RL learner for larger problems. The results support our hypothesis about the capability of the GBML method to induce tutorial tactics. This suggests that the GBML method should be favorable in developing real-world ITS applications in the domain of tutorial tactics induction.

  8. Challenges in adapting imitation and reinforcement learning to compliant robots

    Directory of Open Access Journals (Sweden)

    Calinon Sylvain

    2011-12-01

    Full Text Available There is an exponential increase of the range of tasks that robots are forecasted to accomplish. (Reprogramming these robots becomes a critical issue for their commercialization and for their applications to real-world scenarios in which users without expertise in robotics wish to adapt the robot to their needs. This paper addresses the problem of designing userfriendly human-robot interfaces to transfer skills in a fast and efficient manner. This paper presents recent work conducted at the Learning and Interaction group at ADVR-IIT, ranging from skill acquisition through kinesthetic teaching to self-refinement strategies initiated from demonstrations. Our group started to explore the use of imitation and exploration strategies that can take advantage of the compliant capabilities of recent robot hardware and control architectures.

  9. Multichannel sound reinforcement systems at work in a learning environment

    Science.gov (United States)

    Malek, John; Campbell, Colin

    2003-04-01

    Many people have experienced the entertaining benefits of a surround sound system, either in their own home or in a movie theater, but another application exists for multichannel sound that has for the most part gone unused. This is the application of multichannel sound systems to the learning environment. By incorporating a 7.1 surround processor and a touch panel interface programmable control system, the main lecture hall at the University of Michigan Taubman College of Architecture and Urban Planning has been converted from an ordinary lecture hall to a working audiovisual laboratory. The multichannel sound system is used in a wide variety of experiments, including exposure to sounds to test listeners' aural perception of the tonal characteristics of varying pitch, reverberation, speech transmission index, and sound-pressure level. The touch panel's custom interface allows a variety of user groups to control different parts of the AV system and provides preset capability that allows for numerous system configurations.

  10. Performance Comparison of Two Reinforcement Learning Algorithms for Small Mobile Robots

    Czech Academy of Sciences Publication Activity Database

    Neruda, Roman; Slušný, Stanislav

    2009-01-01

    Roč. 2, č. 1 (2009), s. 59-68 ISSN 2005-4297 R&D Projects: GA MŠk(CZ) 1M0567 Grant - others:GA UK(CZ) 7637/2007 Institutional research plan: CEZ:AV0Z10300504 Keywords : reinforcement learning * mobile robots * inteligent agents Subject RIV: IN - Informatics, Computer Science http://www.sersc.org/journals/IJCA/vol2_no1/7.pdf

  11. Vision-based Navigation and Reinforcement Learning Path Finding for Social Robots

    OpenAIRE

    Pérez Sala, Xavier

    2010-01-01

    We propose a robust system for automatic Robot Navigation in uncontrolled en- vironments. The system is composed by three main modules: the Arti cial Vision module, the Reinforcement Learning module, and the behavior control module. The aim of the system is to allow a robot to automatically nd a path that arrives to a pre xed goal. Turn and straight movements in uncontrolled environments are automatically estimated and controlled using the proposed modules. The Arti cial Vi...

  12. TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow

    OpenAIRE

    Hafner, Danijar; Davidson, James; Vanhoucke, Vincent

    2017-01-01

    We introduce TensorFlow Agents, an efficient infrastructure paradigm for building parallel reinforcement learning algorithms in TensorFlow. We simulate multiple environments in parallel, and group them to perform the neural network computation on a batch rather than individual observations. This allows the TensorFlow execution engine to parallelize computation, without the need for manual synchronization. Environments are stepped in separate Python processes to progress them in parallel witho...

  13. Intrinsically motivated reinforcement learning for human-robot interaction in the real-world.

    Science.gov (United States)

    Qureshi, Ahmed Hussain; Nakamura, Yutaka; Yoshikawa, Yuichiro; Ishiguro, Hiroshi

    2018-03-26

    For a natural social human-robot interaction, it is essential for a robot to learn the human-like social skills. However, learning such skills is notoriously hard due to the limited availability of direct instructions from people to teach a robot. In this paper, we propose an intrinsically motivated reinforcement learning framework in which an agent gets the intrinsic motivation-based rewards through the action-conditional predictive model. By using the proposed method, the robot learned the social skills from the human-robot interaction experiences gathered in the real uncontrolled environments. The results indicate that the robot not only acquired human-like social skills but also took more human-like decisions, on a test dataset, than a robot which received direct rewards for the task achievement. Copyright © 2018 Elsevier Ltd. All rights reserved.

  14. Product Distribution Theory for Control of Multi-Agent Systems

    Science.gov (United States)

    Lee, Chia Fan; Wolpert, David H.

    2004-01-01

    Product Distribution (PD) theory is a new framework for controlling Multi-Agent Systems (MAS's). First we review one motivation of PD theory, as the information-theoretic extension of conventional full-rationality game theory to the case of bounded rational agents. In this extension the equilibrium of the game is the optimizer of a Lagrangian of the (probability distribution of) the joint stare of the agents. Accordingly we can consider a team game in which the shared utility is a performance measure of the behavior of the MAS. For such a scenario the game is at equilibrium - the Lagrangian is optimized - when the joint distribution of the agents optimizes the system's expected performance. One common way to find that equilibrium is to have each agent run a reinforcement learning algorithm. Here we investigate the alternative of exploiting PD theory to run gradient descent on the Lagrangian. We present computer experiments validating some of the predictions of PD theory for how best to do that gradient descent. We also demonstrate how PD theory can improve performance even when we are not allowed to rerun the MAS from different initial conditions, a requirement implicit in some previous work.

  15. Adaptive, Distributed Control of Constrained Multi-Agent Systems

    Science.gov (United States)

    Bieniawski, Stefan; Wolpert, David H.

    2004-01-01

    Product Distribution (PO) theory was recently developed as a broad framework for analyzing and optimizing distributed systems. Here we demonstrate its use for adaptive distributed control of Multi-Agent Systems (MASS), i.e., for distributed stochastic optimization using MAS s. First we review one motivation of PD theory, as the information-theoretic extension of conventional full-rationality game theory to the case of bounded rational agents. In this extension the equilibrium of the game is the optimizer of a Lagrangian of the (Probability dist&&on on the joint state of the agents. When the game in question is a team game with constraints, that equilibrium optimizes the expected value of the team game utility, subject to those constraints. One common way to find that equilibrium is to have each agent run a Reinforcement Learning (E) algorithm. PD theory reveals this to be a particular type of search algorithm for minimizing the Lagrangian. Typically that algorithm i s quite inefficient. A more principled alternative is to use a variant of Newton's method to minimize the Lagrangian. Here we compare this alternative to RL-based search in three sets of computer experiments. These are the N Queen s problem and bin-packing problem from the optimization literature, and the Bar problem from the distributed RL literature. Our results confirm that the PD-theory-based approach outperforms the RL-based scheme in all three domains.

  16. Optimal Wonderful Life Utility Functions in Multi-Agent Systems

    Science.gov (United States)

    Wolpert, David H.; Tumer, Kagan; Swanson, Keith (Technical Monitor)

    2000-01-01

    The mathematics of Collective Intelligence (COINs) is concerned with the design of multi-agent systems so as to optimize an overall global utility function when those systems lack centralized communication and control. Typically in COINs each agent runs a distinct Reinforcement Learning (RL) algorithm, so that much of the design problem reduces to how best to initialize/update each agent's private utility function, as far as the ensuing value of the global utility is concerned. Traditional team game solutions to this problem assign to each agent the global utility as its private utility function. In previous work we used the COIN framework to derive the alternative Wonderful Life Utility (WLU), and experimentally established that having the agents use it induces global utility performance up to orders of magnitude superior to that induced by use of the team game utility. The WLU has a free parameter (the clamping parameter) which we simply set to zero in that previous work. Here we derive the optimal value of the clamping parameter, and demonstrate experimentally that using that optimal value can result in significantly improved performance over that of clamping to zero, over and above the improvement beyond traditional approaches.

  17. Reinforcement learning of targeted movement in a spiking neuronal model of motor cortex.

    Directory of Open Access Journals (Sweden)

    George L Chadderdon

    Full Text Available Sensorimotor control has traditionally been considered from a control theory perspective, without relation to neurobiology. In contrast, here we utilized a spiking-neuron model of motor cortex and trained it to perform a simple movement task, which consisted of rotating a single-joint "forearm" to a target. Learning was based on a reinforcement mechanism analogous to that of the dopamine system. This provided a global reward or punishment signal in response to decreasing or increasing distance from hand to target, respectively. Output was partially driven by Poisson motor babbling, creating stochastic movements that could then be shaped by learning. The virtual forearm consisted of a single segment rotated around an elbow joint, controlled by flexor and extensor muscles. The model consisted of 144 excitatory and 64 inhibitory event-based neurons, each with AMPA, NMDA, and GABA synapses. Proprioceptive cell input to this model encoded the 2 muscle lengths. Plasticity was only enabled in feedforward connections between input and output excitatory units, using spike-timing-dependent eligibility traces for synaptic credit or blame assignment. Learning resulted from a global 3-valued signal: reward (+1, no learning (0, or punishment (-1, corresponding to phasic increases, lack of change, or phasic decreases of dopaminergic cell firing, respectively. Successful learning only occurred when both reward and punishment were enabled. In this case, 5 target angles were learned successfully within 180 s of simulation time, with a median error of 8 degrees. Motor babbling allowed exploratory learning, but decreased the stability of the learned behavior, since the hand continued moving after reaching the target. Our model demonstrated that a global reinforcement signal, coupled with eligibility traces for synaptic plasticity, can train a spiking sensorimotor network to perform goal-directed motor behavior.

  18. Reinforcement learning of targeted movement in a spiking neuronal model of motor cortex.

    Science.gov (United States)

    Chadderdon, George L; Neymotin, Samuel A; Kerr, Cliff C; Lytton, William W

    2012-01-01

    Sensorimotor control has traditionally been considered from a control theory perspective, without relation to neurobiology. In contrast, here we utilized a spiking-neuron model of motor cortex and trained it to perform a simple movement task, which consisted of rotating a single-joint "forearm" to a target. Learning was based on a reinforcement mechanism analogous to that of the dopamine system. This provided a global reward or punishment signal in response to decreasing or increasing distance from hand to target, respectively. Output was partially driven by Poisson motor babbling, creating stochastic movements that could then be shaped by learning. The virtual forearm consisted of a single segment rotated around an elbow joint, controlled by flexor and extensor muscles. The model consisted of 144 excitatory and 64 inhibitory event-based neurons, each with AMPA, NMDA, and GABA synapses. Proprioceptive cell input to this model encoded the 2 muscle lengths. Plasticity was only enabled in feedforward connections between input and output excitatory units, using spike-timing-dependent eligibility traces for synaptic credit or blame assignment. Learning resulted from a global 3-valued signal: reward (+1), no learning (0), or punishment (-1), corresponding to phasic increases, lack of change, or phasic decreases of dopaminergic cell firing, respectively. Successful learning only occurred when both reward and punishment were enabled. In this case, 5 target angles were learned successfully within 180 s of simulation time, with a median error of 8 degrees. Motor babbling allowed exploratory learning, but decreased the stability of the learned behavior, since the hand continued moving after reaching the target. Our model demonstrated that a global reinforcement signal, coupled with eligibility traces for synaptic plasticity, can train a spiking sensorimotor network to perform goal-directed motor behavior.

  19. Neural mechanisms of reinforcement learning in unmedicated patients with major depressive disorder.

    Science.gov (United States)

    Rothkirch, Marcus; Tonn, Jonas; Köhler, Stephan; Sterzer, Philipp

    2017-04-01

    According to current concepts, major depressive disorder is strongly related to dysfunctional neural processing of motivational information, entailing impairments in reinforcement learning. While computational modelling can reveal the precise nature of neural learning signals, it has not been used to study learning-related neural dysfunctions in unmedicated patients with major depressive disorder so far. We thus aimed at comparing the neural coding of reward and punishment prediction errors, representing indicators of neural learning-related processes, between unmedicated patients with major depressive disorder and healthy participants. To this end, a group of unmedicated patients with major depressive disorder (n = 28) and a group of age- and sex-matched healthy control participants (n = 30) completed an instrumental learning task involving monetary gains and losses during functional magnetic resonance imaging. The two groups did not differ in their learning performance. Patients and control participants showed the same level of prediction error-related activity in the ventral striatum and the anterior insula. In contrast, neural coding of reward prediction errors in the medial orbitofrontal cortex was reduced in patients. Moreover, neural reward prediction error signals in the medial orbitofrontal cortex and ventral striatum showed negative correlations with anhedonia severity. Using a standard instrumental learning paradigm we found no evidence for an overall impairment of reinforcement learning in medication-free patients with major depressive disorder. Importantly, however, the attenuated neural coding of reward in the medial orbitofrontal cortex and the relation between anhedonia and reduced reward prediction error-signalling in the medial orbitofrontal cortex and ventral striatum likely reflect an impairment in experiencing pleasure from rewarding events as a key mechanism of anhedonia in major depressive disorder. © The Author (2017). Published by Oxford

  20. Blended learning for reinforcing dental pharmacology in the clinical years: A qualitative analysis.

    Science.gov (United States)

    Eachempati, Prashanti; Kiran Kumar, K S; Sumanth, K N

    2016-10-01

    Blended learning has become the method of choice in educational institutions because of its systematic integration of traditional classroom teaching and online components. This study aims to analyze student's reflection regarding blended learning in dental pharmacology. A cross-sectional study was conducted in Faculty of Dentistry, Melaka-Manipal Medical College among 3 rd and 4 th year BDS students. A total of 145 dental students, who consented, participate in the study. Students were divided into 14 groups. Nine online sessions followed by nine face-to-face discussions were held. Each session addressed topics related to oral lesions and orofacial pain with pharmacological applications. After each week, students were asked to reflect on blended learning. On completion of 9 weeks, reflections were collected and analyzed. Qualitative analysis was done using thematic analysis model suggested by Braun and Clarke. The four main themes were identified, namely, merits of blended learning, skill in writing prescription for oral diseases, dosages of drugs, and identification of strengths and weakness. In general, the participants had a positive feedback regarding blended learning. Students felt more confident in drug selection and prescription writing. They could recollect the doses better after the online and face-to-face sessions. Most interestingly, the students reflected that they are able to identify their strength and weakness after the blended learning sessions. Blended learning module was successfully implemented for reinforcing dental pharmacology. The results obtained in this study enable us to plan future comparative studies to know the effectiveness of blended learning in dental pharmacology.

  1. Reinforcement learning using a continuous time actor-critic framework with spiking neurons.

    Directory of Open Access Journals (Sweden)

    Nicolas Frémaux

    2013-04-01

    Full Text Available Animals repeat rewarded behaviors, but the physiological basis of reward-based learning has only been partially elucidated. On one hand, experimental evidence shows that the neuromodulator dopamine carries information about rewards and affects synaptic plasticity. On the other hand, the theory of reinforcement learning provides a framework for reward-based learning. Recent models of reward-modulated spike-timing-dependent plasticity have made first steps towards bridging the gap between the two approaches, but faced two problems. First, reinforcement learning is typically formulated in a discrete framework, ill-adapted to the description of natural situations. Second, biologically plausible models of reward-modulated spike-timing-dependent plasticity require precise calculation of the reward prediction error, yet it remains to be shown how this can be computed by neurons. Here we propose a solution to these problems by extending the continuous temporal difference (TD learning of Doya (2000 to the case of spiking neurons in an actor-critic network operating in continuous time, and with continuous state and action representations. In our model, the critic learns to predict expected future rewards in real time. Its activity, together with actual rewards, conditions the delivery of a neuromodulatory TD signal to itself and to the actor, which is responsible for action choice. In simulations, we show that such an architecture can solve a Morris water-maze-like navigation task, in a number of trials consistent with reported animal performance. We also use our model to solve the acrobot and the cartpole problems, two complex motor control tasks. Our model provides a plausible way of computing reward prediction error in the brain. Moreover, the analytically derived learning rule is consistent with experimental evidence for dopamine-modulated spike-timing-dependent plasticity.

  2. 'Proactive' use of cue-context congruence for building reinforcement learning's reward function.

    Science.gov (United States)

    Zsuga, Judit; Biro, Klara; Tajti, Gabor; Szilasi, Magdolna Emma; Papp, Csaba; Juhasz, Bela; Gesztelyi, Rudolf

    2016-10-28

    Reinforcement learning is a fundamental form of learning that may be formalized using the Bellman equation. Accordingly an agent determines the state value as the sum of immediate reward and of the discounted value of future states. Thus the value of state is determined by agent related attributes (action set, policy, discount factor) and the agent's knowledge of the environment embodied by the reward function and hidden environmental factors given by the transition probability. The central objective of reinforcement learning is to solve these two functions outside the agent's control either using, or not using a model. In the present paper, using the proactive model of reinforcement learning we offer insight on how the brain creates simplified representations of the environment, and how these representations are organized to support the identification of relevant stimuli and action. Furthermore, we identify neurobiological correlates of our model by suggesting that the reward and policy functions, attributes of the Bellman equitation, are built by the orbitofrontal cortex (OFC) and the anterior cingulate cortex (ACC), respectively. Based on this we propose that the OFC assesses cue-context congruence to activate the most context frame. Furthermore given the bidirectional neuroanatomical link between the OFC and model-free structures, we suggest that model-based input is incorporated into the reward prediction error (RPE) signal, and conversely RPE signal may be used to update the reward-related information of context frames and the policy underlying action selection in the OFC and ACC, respectively. Furthermore clinical implications for cognitive behavioral interventions are discussed.

  3. A Concise Introduction to Multiagent Systems and Distributed Artificial Intelligence

    CERN Document Server

    Vlassis, Nikos

    2007-01-01

    Multiagent systems is an expanding field that blends classical fields like game theory and decentralized control with modern fields like computer science and machine learning. This monograph provides a concise introduction to the subject, covering the theoretical foundations as well as more recent developments in a coherent and readable manner. The text is centered on the concept of an agent as decision maker. Chapter 1 is a short introduction to the field of multiagent systems. Chapter 2 covers the basic theory of singleagent decision making under uncertainty. Chapter 3 is a brief introductio

  4. Autonomous parsing of behavior in a multi-agent setting

    NARCIS (Netherlands)

    Vanderelst, D.; Barakova, E.I.; Rutkowski, L.; Tadeusiewicz, R.

    2008-01-01

    Imitation learning is a promising route to instruct robotic multi-agent systems. However, imitating agents should be able to decide autonomously what behavior, observed in others, is interesting to copy. Here we investigate whether a simple recurrent network (Elman Net) can be used to extract

  5. A Plant Control Technology Using Reinforcement Learning Method with Automatic Reward Adjustment

    Science.gov (United States)

    Eguchi, Toru; Sekiai, Takaaki; Yamada, Akihiro; Shimizu, Satoru; Fukai, Masayuki

    A control technology using Reinforcement Learning (RL) and Radial Basis Function (RBF) Network has been developed to reduce environmental load substances exhausted from power and industrial plants. This technology consists of the statistic model using RBF Network, which estimates characteristics of plants with respect to environmental load substances, and RL agent, which learns the control logic for the plants using the statistic model. In this technology, it is necessary to design an appropriate reward function given to the agent immediately according to operation conditions and control goals to control plants flexibly. Therefore, we propose an automatic reward adjusting method of RL for plant control. This method adjusts the reward function automatically using information of the statistic model obtained in its learning process. In the simulations, it is confirmed that the proposed method can adjust the reward function adaptively for several test functions, and executes robust control toward the thermal power plant considering the change of operation conditions and control goals.

  6. Optimal medication dosing from suboptimal clinical examples: a deep reinforcement learning approach.

    Science.gov (United States)

    Nemati, Shamim; Ghassemi, Mohammad M; Clifford, Gari D

    2016-08-01

    Misdosing medications with sensitive therapeutic windows, such as heparin, can place patients at unnecessary risk, increase length of hospital stay, and lead to wasted hospital resources. In this work, we present a clinician-in-the-loop sequential decision making framework, which provides an individualized dosing policy adapted to each patient's evolving clinical phenotype. We employed retrospective data from the publicly available MIMIC II intensive care unit database, and developed a deep reinforcement learning algorithm that learns an optimal heparin dosing policy from sample dosing trails and their associated outcomes in large electronic medical records. Using separate training and testing datasets, our model was observed to be effective in proposing heparin doses that resulted in better expected outcomes than the clinical guidelines. Our results demonstrate that a sequential modeling approach, learned from retrospective data, could potentially be used at the bedside to derive individualized patient dosing policies.

  7. Bio-robots automatic navigation with graded electric reward stimulation based on Reinforcement Learning.

    Science.gov (United States)

    Zhang, Chen; Sun, Chao; Gao, Liqiang; Zheng, Nenggan; Chen, Weidong; Zheng, Xiaoxiang

    2013-01-01

    Bio-robots based on brain computer interface (BCI) suffer from the lack of considering the characteristic of the animals in navigation. This paper proposed a new method for bio-robots' automatic navigation combining the reward generating algorithm base on Reinforcement Learning (RL) with the learning intelligence of animals together. Given the graded electrical reward, the animal e.g. the rat, intends to seek the maximum reward while exploring an unknown environment. Since the rat has excellent spatial recognition, the rat-robot and the RL algorithm can convergent to an optimal route by co-learning. This work has significant inspiration for the practical development of bio-robots' navigation with hybrid intelligence.

  8. Off-policy integral reinforcement learning optimal tracking control for continuous-time chaotic systems

    International Nuclear Information System (INIS)

    Wei Qing-Lai; Song Rui-Zhuo; Xiao Wen-Dong; Sun Qiu-Ye

    2015-01-01

    This paper estimates an off-policy integral reinforcement learning (IRL) algorithm to obtain the optimal tracking control of unknown chaotic systems. Off-policy IRL can learn the solution of the HJB equation from the system data generated by an arbitrary control. Moreover, off-policy IRL can be regarded as a direct learning method, which avoids the identification of system dynamics. In this paper, the performance index function is first given based on the system tracking error and control error. For solving the Hamilton–Jacobi–Bellman (HJB) equation, an off-policy IRL algorithm is proposed. It is proven that the iterative control makes the tracking error system asymptotically stable, and the iterative performance index function is convergent. Simulation study demonstrates the effectiveness of the developed tracking control method. (paper)

  9. Universal effect of dynamical reinforcement learning mechanism in spatial evolutionary games

    International Nuclear Information System (INIS)

    Zhang, Hai-Feng; Wu, Zhi-Xi; Wang, Bing-Hong

    2012-01-01

    One of the prototypical mechanisms in understanding the ubiquitous cooperation in social dilemma situations is the win–stay, lose–shift rule. In this work, a generalized win–stay, lose–shift learning model—a reinforcement learning model with dynamic aspiration level—is proposed to describe how humans adapt their social behaviors based on their social experiences. In the model, the players incorporate the information of the outcomes in previous rounds with time-dependent aspiration payoffs to regulate the probability of choosing cooperation. By investigating such a reinforcement learning rule in the spatial prisoner's dilemma game and public goods game, a most noteworthy viewpoint is that moderate greediness (i.e. moderate aspiration level) favors best the development and organization of collective cooperation. The generality of this observation is tested against different regulation strengths and different types of network of interaction as well. We also make comparisons with two recently proposed models to highlight the importance of the mechanism of adaptive aspiration level in supporting cooperation in structured populations

  10. Reinforcement Learning with Autonomous Small Unmanned Aerial Vehicles in Cluttered Environments

    Science.gov (United States)

    Tran, Loc; Cross, Charles; Montague, Gilbert; Motter, Mark; Neilan, James; Qualls, Garry; Rothhaar, Paul; Trujillo, Anna; Allen, B. Danette

    2015-01-01

    We present ongoing work in the Autonomy Incubator at NASA Langley Research Center (LaRC) exploring the efficacy of a data set aggregation approach to reinforcement learning for small unmanned aerial vehicle (sUAV) flight in dense and cluttered environments with reactive obstacle avoidance. The goal is to learn an autonomous flight model using training experiences from a human piloting a sUAV around static obstacles. The training approach uses video data from a forward-facing camera that records the human pilot's flight. Various computer vision based features are extracted from the video relating to edge and gradient information. The recorded human-controlled inputs are used to train an autonomous control model that correlates the extracted feature vector to a yaw command. As part of the reinforcement learning approach, the autonomous control model is iteratively updated with feedback from a human agent who corrects undesired model output. This data driven approach to autonomous obstacle avoidance is explored for simulated forest environments furthering autonomous flight under the tree canopy research. This enables flight in previously inaccessible environments which are of interest to NASA researchers in Earth and Atmospheric sciences.

  11. Multiagent scheduling models and algorithms

    CERN Document Server

    Agnetis, Alessandro; Gawiejnowicz, Stanisław; Pacciarelli, Dario; Soukhal, Ameur

    2014-01-01

    This book presents multi-agent scheduling models in which subsets of jobs sharing the same resources are evaluated by different criteria. It discusses complexity results, approximation schemes, heuristics and exact algorithms.

  12. Multiagent distributed watershed management

    Science.gov (United States)

    Giuliani, M.; Castelletti, A.; Amigoni, F.; Cai, X.

    2012-04-01

    Deregulation and democratization of water along with increasing environmental awareness are challenging integrated water resources planning and management worldwide. The traditional centralized approach to water management, as described in much of water resources literature, is often unfeasible in most of the modern social and institutional contexts. Thus it should be reconsidered from a more realistic and distributed perspective, in order to account for the presence of multiple and often independent Decision Makers (DMs) and many conflicting stakeholders. Game theory based approaches are often used to study these situations of conflict (Madani, 2010), but they are limited to a descriptive perspective. Multiagent systems (see Wooldridge, 2009), instead, seem to be a more suitable paradigm because they naturally allow to represent a set of self-interested agents (DMs and/or stakeholders) acting in a distributed decision process at the agent level, resulting in a promising compromise alternative between the ideal centralized solution and the actual uncoordinated practices. Casting a water management problem in a multiagent framework allows to exploit the techniques and methods that are already available in this field for solving distributed optimization problems. In particular, in Distributed Constraint Satisfaction Problems (DCSP, see Yokoo et al., 2000), each agent controls some variables according to his own utility function but has to satisfy inter-agent constraints; while in Distributed Constraint Optimization Problems (DCOP, see Modi et al., 2005), the problem is generalized by introducing a global objective function to be optimized that requires a coordination mechanism between the agents. In this work, we apply a DCSP-DCOP based approach to model a steady state hypothetical watershed management problem (Yang et al., 2009), involving several active human agents (i.e. agents who make decisions) and reactive ecological agents (i.e. agents representing

  13. Dynamic pricing and automated resource allocation for complex information services reinforcement learning and combinatorial auctions

    CERN Document Server

    Schwind, Michael; Fandel, G

    2007-01-01

    Many firms provide their customers with online information products which require limited resources such as server capacity. This book develops allocation mechanisms that aim to ensure an efficient resource allocation in modern IT-services. Recent methods of artificial intelligence, such as neural networks and reinforcement learning, and nature-oriented optimization methods, such as genetic algorithms and simulated annealing, are advanced and applied to allocation processes in distributed IT-infrastructures, e.g. grid systems. The author presents two methods, both of which using the users??? w

  14. Brain Circuits of Methamphetamine Place Reinforcement Learning: The Role of the Hippocampus-VTA Loop.

    Science.gov (United States)

    Keleta, Yonas B; Martinez, Joe L

    2012-03-01

    The reinforcing effects of addictive drugs including methamphetamine (METH) involve the midbrain ventral tegmental area (VTA). VTA is primary source of dopamine (DA) to the nucleus accumbens (NAc) and the ventral hippocampus (VHC). These three brain regions are functionally connected through the hippocampal-VTA loop that includes two main neural pathways: the bottom-up pathway and the top-down pathway. In this paper, we take the view that addiction is a learning process. Therefore, we tested the involvement of the hippocampus in reinforcement learning by studying conditioned place preference (CPP) learning by sequentially conditioning each of the three nuclei in either the bottom-up order of conditioning; VTA, then VHC, finally NAc, or the top-down order; VHC, then VTA, finally NAc. Following habituation, the rats underwent experimental modules consisting of two conditioning trials each followed by immediate testing (test 1 and test 2) and two additional tests 24 h (test 3) and/or 1 week following conditioning (test 4). The module was repeated three times for each nucleus. The results showed that METH, but not Ringer's, produced positive CPP following conditioning each brain area in the bottom-up order. In the top-down order, METH, but not Ringer's, produced either an aversive CPP or no learning effect following conditioning each nucleus of interest. In addition, METH place aversion was antagonized by coadministration of the N-methyl-d-aspartate (NMDA) receptor antagonist MK801, suggesting that the aversion learning was an NMDA receptor activation-dependent process. We conclude that the hippocampus is a critical structure in the reward circuit and hence suggest that the development of target-specific therapeutics for the control of addiction emphasizes on the hippocampus-VTA top-down connection.

  15. Learning to reach by reinforcement learning using a receptive field based function approximation approach with continuous actions.

    Science.gov (United States)

    Tamosiunaite, Minija; Asfour, Tamim; Wörgötter, Florentin

    2009-03-01

    Reinforcement learning methods can be used in robotics applications especially for specific target-oriented problems, for example the reward-based recalibration of goal directed actions. To this end still relatively large and continuous state-action spaces need to be efficiently handled. The goal of this paper is, thus, to develop a novel, rather simple method which uses reinforcement learning with function approximation in conjunction with different reward-strategies for solving such problems. For the testing of our method, we use a four degree-of-freedom reaching problem in 3D-space simulated by a two-joint robot arm system with two DOF each. Function approximation is based on 4D, overlapping kernels (receptive fields) and the state-action space contains about 10,000 of these. Different types of reward structures are being compared, for example, reward-on- touching-only against reward-on-approach. Furthermore, forbidden joint configurations are punished. A continuous action space is used. In spite of a rather large number of states and the continuous action space these reward/punishment strategies allow the system to find a good solution usually within about 20 trials. The efficiency of our method demonstrated in this test scenario suggests that it might be possible to use it on a real robot for problems where mixed rewards can be defined in situations where other types of learning might be difficult.

  16. Linking Individual Learning Styles to Approach-Avoidance Motivational Traits and Computational Aspects of Reinforcement Learning.

    Directory of Open Access Journals (Sweden)

    Kristoffer Carl Aberg

    Full Text Available Learning how to gain rewards (approach learning and avoid punishments (avoidance learning is fundamental for everyday life. While individual differences in approach and avoidance learning styles have been related to genetics and aging, the contribution of personality factors, such as traits, remains undetermined. Moreover, little is known about the computational mechanisms mediating differences in learning styles. Here, we used a probabilistic selection task with positive and negative feedbacks, in combination with computational modelling, to show that individuals displaying better approach (vs. avoidance learning scored higher on measures of approach (vs. avoidance trait motivation, but, paradoxically, also displayed reduced learning speed following positive (vs. negative outcomes. These data suggest that learning different types of information depend on associated reward values and internal motivational drives, possibly determined by personality traits.

  17. Linking Individual Learning Styles to Approach-Avoidance Motivational Traits and Computational Aspects of Reinforcement Learning

    Science.gov (United States)

    Carl Aberg, Kristoffer; Doell, Kimberly C.; Schwartz, Sophie

    2016-01-01

    Learning how to gain rewards (approach learning) and avoid punishments (avoidance learning) is fundamental for everyday life. While individual differences in approach and avoidance learning styles have been related to genetics and aging, the contribution of personality factors, such as traits, remains undetermined. Moreover, little is known about the computational mechanisms mediating differences in learning styles. Here, we used a probabilistic selection task with positive and negative feedbacks, in combination with computational modelling, to show that individuals displaying better approach (vs. avoidance) learning scored higher on measures of approach (vs. avoidance) trait motivation, but, paradoxically, also displayed reduced learning speed following positive (vs. negative) outcomes. These data suggest that learning different types of information depend on associated reward values and internal motivational drives, possibly determined by personality traits. PMID:27851807

  18. An analysis of intergroup rivalry using Ising model and reinforcement learning

    Science.gov (United States)

    Zhao, Feng-Fei; Qin, Zheng; Shao, Zhuo

    2014-01-01

    Modeling of intergroup rivalry can help us better understand economic competitions, political elections and other similar activities. The result of intergroup rivalry depends on the co-evolution of individual behavior within one group and the impact from the rival group. In this paper, we model the rivalry behavior using Ising model. Different from other simulation studies using Ising model, the evolution rules of each individual in our model are not static, but have the ability to learn from historical experience using reinforcement learning technique, which makes the simulation more close to real human behavior. We studied the phase transition in intergroup rivalry and focused on the impact of the degree of social freedom, the personality of group members and the social experience of individuals. The results of computer simulation show that a society with a low degree of social freedom and highly educated, experienced individuals is more likely to be one-sided in intergroup rivalry.

  19. Pedunculopontine tegmental nucleus lesions impair stimulus--reward learning in autoshaping and conditioned reinforcement paradigms.

    Science.gov (United States)

    Inglis, W L; Olmstead, M C; Robbins, T W

    2000-04-01

    The role of the pedunculopontine tegmental nucleus (PPTg) in stimulus-reward learning was assessed by testing the effects of PPTg lesions on performance in visual autoshaping and conditioned reinforcement (CRf) paradigms. Rats with PPTg lesions were unable to learn an association between a conditioned stimulus (CS) and a primary reward in either paradigm. In the autoshaping experiment, PPTg-lesioned rats approached the CS+ and CS- with equal frequency, and the latencies to respond to the two stimuli did not differ. PPTg lesions also disrupted discriminated approaches to an appetitive CS in the CRf paradigm and completely abolished the acquisition of responding with CRf. These data are discussed in the context of a possible cognitive function of the PPTg, particularly in terms of lesion-induced disruptions of attentional processes that are mediated by the thalamus.

  20. Reinforcement learning solution for HJB equation arising in constrained optimal control problem.

    Science.gov (United States)

    Luo, Biao; Wu, Huai-Ning; Huang, Tingwen; Liu, Derong

    2015-11-01

    The constrained optimal control problem depends on the solution of the complicated Hamilton-Jacobi-Bellman equation (HJBE). In this paper, a data-based off-policy reinforcement learning (RL) method is proposed, which learns the solution of the HJBE and the optimal control policy from real system data. One important feature of the off-policy RL is that its policy evaluation can be realized with data generated by other behavior policies, not necessarily the target policy, which solves the insufficient exploration problem. The convergence of the off-policy RL is proved by demonstrating its equivalence to the successive approximation approach. Its implementation procedure is based on the actor-critic neural networks structure, where the function approximation is conducted with linearly independent basis functions. Subsequently, the convergence of the implementation procedure with function approximation is also proved. Finally, its effectiveness is verified through computer simulations. Copyright © 2015 Elsevier Ltd. All rights reserved.

  1. Reinforcement learning for a biped robot based on a CPG-actor-critic method.

    Science.gov (United States)

    Nakamura, Yutaka; Mori, Takeshi; Sato, Masa-aki; Ishii, Shin

    2007-08-01

    Animals' rhythmic movements, such as locomotion, are considered to be controlled by neural circuits called central pattern generators (CPGs), which generate oscillatory signals. Motivated by this biological mechanism, studies have been conducted on the rhythmic movements controlled by CPG. As an autonomous learning framework for a CPG controller, we propose in this article a reinforcement learning method we call the "CPG-actor-critic" method. This method introduces a new architecture to the actor, and its training is roughly based on a stochastic policy gradient algorithm presented recently. We apply this method to an automatic acquisition problem of control for a biped robot. Computer simulations show that training of the CPG can be successfully performed by our method, thus allowing the biped robot to not only walk stably but also adapt to environmental changes.

  2. The role of multiple neuromodulators in reinforcement learning that is based on competition between eligibility traces

    Directory of Open Access Journals (Sweden)

    Marco A Huertas

    2016-12-01

    Full Text Available The ability to maximize reward and avoid punishment is essential for animal survival. Reinforcement learning (RL refers to the algorithms used by biological or artificial systems to learn how to maximize reward or avoid negative outcomes based on past experiences. While RL is also important in machine learning, the types of mechanistic constraints encountered by biological machinery might be different than those for artificial systems. Two major problems encountered by RL are how to relate a stimulus with a reinforcing signal that is delayed in time (temporal credit assignment, and how to stop learning once the target behaviors are attained (stopping rule. To address the first problem, synaptic eligibility traces were introduced, bridging the temporal gap between a stimulus and its reward. Although these were mere theoretical constructs, recent experiements have provided evidence of their existence. These experiments also reveal that the presence of specific neuromodulators converts the traces into changes in synaptic efficacy. A mechanistic implementation of the stopping rule usually assumes the inhibition of the reward nucleus; however, recent experimental results have shown that learning terminates at the appropriate network state even in setups where the reward cannot be inhibited. In an effort to describe a learning rule that solves the temporal credit assignment problem and implements a biologically plausible stopping rule, we proposed a model based on two separate synaptic eligibility traces, one for long-term potentiation (LTP and one for long-term depression (LTD, each obeying different dynamics and having different effective magnitudes. The model has been shown to successfully generate stable learning in recurrent networks. Although the model assumes the presence of a single neuromodulator, evidence indicates that there are different neuromodulators for expressing the different traces. What could be the role of different

  3. The Role of Multiple Neuromodulators in Reinforcement Learning That Is Based on Competition between Eligibility Traces.

    Science.gov (United States)

    Huertas, Marco A; Schwettmann, Sarah E; Shouval, Harel Z

    2016-01-01

    The ability to maximize reward and avoid punishment is essential for animal survival. Reinforcement learning (RL) refers to the algorithms used by biological or artificial systems to learn how to maximize reward or avoid negative outcomes based on past experiences. While RL is also important in machine learning, the types of mechanistic constraints encountered by biological machinery might be different than those for artificial systems. Two major problems encountered by RL are how to relate a stimulus with a reinforcing signal that is delayed in time (temporal credit assignment), and how to stop learning once the target behaviors are attained (stopping rule). To address the first problem synaptic eligibility traces were introduced, bridging the temporal gap between a stimulus and its reward. Although, these were mere theoretical constructs, recent experiments have provided evidence of their existence. These experiments also reveal that the presence of specific neuromodulators converts the traces into changes in synaptic efficacy. A mechanistic implementation of the stopping rule usually assumes the inhibition of the reward nucleus; however, recent experimental results have shown that learning terminates at the appropriate network state even in setups where the reward nucleus cannot be inhibited. In an effort to describe a learning rule that solves the temporal credit assignment problem and implements a biologically plausible stopping rule, we proposed a model based on two separate synaptic eligibility traces, one for long-term potentiation (LTP) and one for long-term depression (LTD), each obeying different dynamics and having different effective magnitudes. The model has been shown to successfully generate stable learning in recurrent networks. Although, the model assumes the presence of a single neuromodulator, evidence indicates that there are different neuromodulators for expressing the different traces. What could be the role of different neuromodulators for

  4. Optimal and Scalable Caching for 5G Using Reinforcement Learning of Space-Time Popularities

    Science.gov (United States)

    Sadeghi, Alireza; Sheikholeslami, Fatemeh; Giannakis, Georgios B.

    2018-02-01

    Small basestations (SBs) equipped with caching units have potential to handle the unprecedented demand growth in heterogeneous networks. Through low-rate, backhaul connections with the backbone, SBs can prefetch popular files during off-peak traffic hours, and service them to the edge at peak periods. To intelligently prefetch, each SB must learn what and when to cache, while taking into account SB memory limitations, the massive number of available contents, the unknown popularity profiles, as well as the space-time popularity dynamics of user file requests. In this work, local and global Markov processes model user requests, and a reinforcement learning (RL) framework is put forth for finding the optimal caching policy when the transition probabilities involved are unknown. Joint consideration of global and local popularity demands along with cache-refreshing costs allow for a simple, yet practical asynchronous caching approach. The novel RL-based caching relies on a Q-learning algorithm to implement the optimal policy in an online fashion, thus enabling the cache control unit at the SB to learn, track, and possibly adapt to the underlying dynamics. To endow the algorithm with scalability, a linear function approximation of the proposed Q-learning scheme is introduced, offering faster convergence as well as reduced complexity and memory requirements. Numerical tests corroborate the merits of the proposed approach in various realistic settings.

  5. Energy Management Strategy for a Hybrid Electric Vehicle Based on Deep Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Yue Hu

    2018-01-01

    Full Text Available An energy management strategy (EMS is important for hybrid electric vehicles (HEVs since it plays a decisive role on the performance of the vehicle. However, the variation of future driving conditions deeply influences the effectiveness of the EMS. Most existing EMS methods simply follow predefined rules that are not adaptive to different driving conditions online. Therefore, it is useful that the EMS can learn from the environment or driving cycle. In this paper, a deep reinforcement learning (DRL-based EMS is designed such that it can learn to select actions directly from the states without any prediction or predefined rules. Furthermore, a DRL-based online learning architecture is presented. It is significant for applying the DRL algorithm in HEV energy management under different driving conditions. Simulation experiments have been conducted using MATLAB and Advanced Vehicle Simulator (ADVISOR co-simulation. Experimental results validate the effectiveness of the DRL-based EMS compared with the rule-based EMS in terms of fuel economy. The online learning architecture is also proved to be effective. The proposed method ensures the optimality, as well as real-time applicability, in HEVs.

  6. Intrinsic interactive reinforcement learning - Using error-related potentials for real world human-robot interaction.

    Science.gov (United States)

    Kim, Su Kyoung; Kirchner, Elsa Andrea; Stefes, Arne; Kirchner, Frank

    2017-12-14

    Reinforcement learning (RL) enables robots to learn its optimal behavioral strategy in dynamic environments based on feedback. Explicit human feedback during robot RL is advantageous, since an explicit reward function can be easily adapted. However, it is very demanding and tiresome for a human to continuously and explicitly generate feedback. Therefore, the development of implicit approaches is of high relevance. In this paper, we used an error-related potential (ErrP), an event-related activity in the human electroencephalogram (EEG), as an intrinsically generated implicit feedback (rewards) for RL. Initially we validated our approach with seven subjects in a simulated robot learning scenario. ErrPs were detected online in single trial with a balanced accuracy (bACC) of 91%, which was sufficient to learn to recognize gestures and the correct mapping between human gestures and robot actions in parallel. Finally, we validated our approach in a real robot scenario, in which seven subjects freely chose gestures and the real robot correctly learned the mapping between gestures and actions (ErrP detection (90% bACC)). In this paper, we demonstrated that intrinsically generated EEG-based human feedback in RL can successfully be used to implicitly improve gesture-based robot control during human-robot interaction. We call our approach intrinsic interactive RL.

  7. Reinforcement Learning Based Data Self-Destruction Scheme for Secured Data Management

    Directory of Open Access Journals (Sweden)

    Young Ki Kim

    2018-04-01

    Full Text Available As technologies and services that leverage cloud computing have evolved, the number of businesses and individuals who use them are increasing rapidly. In the course of using cloud services, as users store and use data that include personal information, research on privacy protection models to protect sensitive information in the cloud environment is becoming more important. As a solution to this problem, a self-destructing scheme has been proposed that prevents the decryption of encrypted user data after a certain period of time using a Distributed Hash Table (DHT network. However, the existing self-destructing scheme does not mention how to set the number of key shares and the threshold value considering the environment of the dynamic DHT network. This paper proposes a method to set the parameters to generate the key shares needed for the self-destructing scheme considering the availability and security of data. The proposed method defines state, action, and reward of the reinforcement learning model based on the similarity of the graph, and applies the self-destructing scheme process by updating the parameter based on the reinforcement learning model. Through the proposed technique, key sharing parameters can be set in consideration of data availability and security in dynamic DHT network environments.

  8. Reinforcement learning of self-regulated β-oscillations for motor restoration in chronic stroke

    Directory of Open Access Journals (Sweden)

    Georgios eNaros

    2015-07-01

    Full Text Available Neurofeedback training of motor imagery-related brain-states with brain-machine interfaces (BMI is currently being explored prior to standard physiotherapy to improve the motor outcome of stroke rehabilitation. Pilot studies suggest that such a priming intervention before physiotherapy might increase the responsiveness of the brain to the subsequent physiotherapy, thereby improving the clinical outcome. However, there is little evidence up to now that these BMI-based interventions have achieved operate conditioning of specific brain states that facilitate task-specific functional gains beyond the practice of primed physiotherapy. In this context, we argue that BMI technology needs to aim at physiological features relevant for the targeted behavioral gain. Moreover, this therapeutic intervention has to be informed by concepts of reinforcement learning to develop its full potential. Such a refined neurofeedback approach would need to address the following issues (1 Defining a physiological feedback target specific to the intended behavioral gain, e.g. β-band oscillations for cortico-muscular communication. This targeted brain state could well be different from the brain state optimal for the neurofeedback task (2 Selecting a BMI classification and thresholding approach on the basis of learning principles, i.e. balancing challenge and reward of the neurofeedback task instead of maximizing the classification accuracy of the feedback device (3 Adjusting the feedback in the course of the training period to account for the cognitive load and the learning experience of the participant. The proposed neurofeedback strategy provides evidence for the feasibility of the suggested approach by demonstrating that dynamic threshold adaptation based on reinforcement learning may lead to frequency-specific operant conditioning of β-band oscillations paralleled by task-specific motor improvement; a proposal that requires investigation in a larger cohort of stroke

  9. Multi-Objective Reinforcement Learning-Based Deep Neural Networks for Cognitive Space Communications

    Science.gov (United States)

    Ferreria, Paulo Victor R.; Paffenroth, Randy; Wyglinski, Alexander M.; Hackett, Timothy M.; Bilen, Sven G.; Reinhart, Richard C.; Mortensen, Dale J.

    2017-01-01

    Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

  10. Variability in Dopamine Genes Dissociates Model-Based and Model-Free Reinforcement Learning.

    Science.gov (United States)

    Doll, Bradley B; Bath, Kevin G; Daw, Nathaniel D; Frank, Michael J

    2016-01-27

    Considerable evidence suggests that multiple learning systems can drive behavior. Choice can proceed reflexively from previous actions and their associated outcomes, as captured by "model-free" learning algorithms, or flexibly from prospective consideration of outcomes that might occur, as captured by "model-based" learning algorithms. However, differential contributions of dopamine to these systems are poorly understood. Dopamine is widely thought to support model-free learning by modulating plasticity in striatum. Model-based learning may also be affected by these striatal effects, or by other dopaminergic effects elsewhere, notably on prefrontal working memory function. Indeed, prominent demonstrations linking striatal dopamine to putatively model-free learning did not rule out model-based effects, whereas other studies have reported dopaminergic modulation of verifiably model-based learning, but without distinguishing a prefrontal versus striatal locus. To clarify the relationships between dopamine, neural systems, and learning strategies, we combine a genetic association approach in humans with two well-studied reinforcement learning tasks: one isolating model-based from model-free behavior and the other sensitive to key aspects of striatal plasticity. Prefrontal function was indexed by a polymorphism in the COMT gene, differences of which reflect dopamine levels in the prefrontal cortex. This polymorphism has been associated with differences in prefrontal activity and working memory. Striatal function was indexed by a gene coding for DARPP-32, which is densely expressed in the striatum where it is necessary for synaptic plasticity. We found evidence for our hypothesis that variations in prefrontal dopamine relate to model-based learning, whereas variations in striatal dopamine function relate to model-free learning. Decisions can stem reflexively from their previously associated outcomes or flexibly from deliberative consideration of potential choice outcomes

  11. Investigation of Drive-Reinforcement Learning and Application of Learning to Flight Control

    Science.gov (United States)

    1993-08-01

    WL-TR-93-1153 INVESTIGATION OF DRIVE-REINFORCEMEN% LEARNING AND APPLICATION OF LEARNING TO FLIGHT CONTROL AD-A277 442 WALTER L. BAKER (ED), STEPHEN ...OF LEARNING TO FUIGHT CONTROL PE 62204 ___ ___ ___ ___ __ ___ ___ ___ ___ ___ ___ __ PR 2003 6. AUTHOR(S) TA 05 WALTER L. BAKER (ED), STEPHEN C. ATKINS...34 Computers and Thought, E. A. Freigenbaum and J. Feldman (eds.), Mc- Graw Hill, New York, (1959). [19] Holland, J. H., "Escaping Brittleness: The Possibility

  12. Within- and across-trial dynamics of human EEG reveal cooperative interplay between reinforcement learning and working memory.

    Science.gov (United States)

    Collins, Anne G E; Frank, Michael J

    2018-03-06

    Learning from rewards and punishments is essential to survival and facilitates flexible human behavior. It is widely appreciated that multiple cognitive and reinforcement learning systems contribute to decision-making, but the nature of their interactions is elusive. Here, we leverage methods for extracting trial-by-trial indices of reinforcement learning (RL) and working memory (WM) in human electro-encephalography to reveal single-trial computations beyond that afforded by behavior alone. Neural dynamics confirmed that increases in neural expectation were predictive of reduced neural surprise in the following feedback period, supporting central tenets of RL models. Within- and cross-trial dynamics revealed a cooperative interplay between systems for learning, in which WM contributes expectations to guide RL, despite competition between systems during choice. Together, these results provide a deeper understanding of how multiple neural systems interact for learning and decision-making and facilitate analysis of their disruption in clinical populations.

  13. Integral reinforcement learning for continuous-time input-affine nonlinear systems with simultaneous invariant explorations.

    Science.gov (United States)

    Lee, Jae Young; Park, Jin Bae; Choi, Yoon Ho

    2015-05-01

    This paper focuses on a class of reinforcement learning (RL) algorithms, named integral RL (I-RL), that solve continuous-time (CT) nonlinear optimal control problems with input-affine system dynamics. First, we extend the concepts of exploration, integral temporal difference, and invariant admissibility to the target CT nonlinear system that is governed by a control policy plus a probing signal called an exploration. Then, we show input-to-state stability (ISS) and invariant admissibility of the closed-loop systems with the policies generated by integral policy iteration (I-PI) or invariantly admissible PI (IA-PI) method. Based on these, three online I-RL algorithms named explorized I-PI and integral Q -learning I, II are proposed, all of which generate the same convergent sequences as I-PI and IA-PI under the required excitation condition on the exploration. All the proposed methods are partially or completely model free, and can simultaneously explore the state space in a stable manner during the online learning processes. ISS, invariant admissibility, and convergence properties of the proposed methods are also investigated, and related with these, we show the design principles of the exploration for safe learning. Neural-network-based implementation methods for the proposed schemes are also presented in this paper. Finally, several numerical simulations are carried out to verify the effectiveness of the proposed methods.

  14. Reinforcement learning for partially observable dynamic processes: adaptive dynamic programming using measured output data.

    Science.gov (United States)

    Lewis, F L; Vamvoudakis, Kyriakos G

    2011-02-01

    Approximate dynamic programming (ADP) is a class of reinforcement learning methods that have shown their importance in a variety of applications, including feedback control of dynamical systems. ADP generally requires full information about the system internal states, which is usually not available in practical situations. In this paper, we show how to implement ADP methods using only measured input/output data from the system. Linear dynamical systems with deterministic behavior are considered herein, which are systems of great interest in the control system community. In control system theory, these types of methods are referred to as output feedback (OPFB). The stochastic equivalent of the systems dealt with in this paper is a class of partially observable Markov decision processes. We develop both policy iteration and value iteration algorithms that converge to an optimal controller that requires only OPFB. It is shown that, similar to Q -learning, the new methods have the important advantage that knowledge of the system dynamics is not needed for the implementation of these learning algorithms or for the OPFB control. Only the order of the system, as well as an upper bound on its "observability index," must be known. The learned OPFB controller is in the form of a polynomial autoregressive moving-average controller that has equivalent performance with the optimal state variable feedback gain.

  15. Design issues of a reinforcement-based self-learning fuzzy controller for petrochemical process control

    Science.gov (United States)

    Yen, John; Wang, Haojin; Daugherity, Walter C.

    1992-01-01

    Fuzzy logic controllers have some often-cited advantages over conventional techniques such as PID control, including easier implementation, accommodation to natural language, and the ability to cover a wider range of operating conditions. One major obstacle that hinders the broader application of fuzzy logic controllers is the lack of a systematic way to develop and modify their rules; as a result the creation and modification of fuzzy rules often depends on trial and error or pure experimentation. One of the proposed approaches to address this issue is a self-learning fuzzy logic controller (SFLC) that uses reinforcement learning techniques to learn the desirability of states and to adjust the consequent part of its fuzzy control rules accordingly. Due to the different dynamics of the controlled processes, the performance of a self-learning fuzzy controller is highly contingent on its design. The design issue has not received sufficient attention. The issues related to the design of a SFLC for application to a petrochemical process are discussed, and its performance is compared with that of a PID and a self-tuning fuzzy logic controller.

  16. DAT1-Genotype and Menstrual Cycle, but Not Hormonal Contraception, Modulate Reinforcement Learning: Preliminary Evidence.

    Science.gov (United States)

    Jakob, Kristina; Ehrentreich, Hanna; Holtfrerich, Sarah K C; Reimers, Luise; Diekhof, Esther K

    2018-01-01

    Hormone by genotype interactions have been widely ignored by cognitive neuroscience. Yet, the dependence of cognitive performance on both baseline dopamine (DA) and current 17ß-estradiol (E2) level argues for their combined effect also in the context of reinforcement learning. Here, we assessed how the interaction between the natural rise of E2 in the late follicular phase (FP) and the 40 base-pair variable number tandem repeat polymorphism of the dopamine transporter (DAT1) affects reinforcement learning capacity. 30 women with a regular menstrual cycle performed a probabilistic feedback learning task twice during the early and late FP. In addition, 39 women, who took hormonal contraceptives (HC) to suppress natural ovulation, were tested during the "pill break" and the intake phase of HC. The present data show that DAT1-genotype may interact with transient hormonal state, but only in women with a natural menstrual cycle. We found that carriers of the 9-repeat allele (9RP) experienced a significant decrease in the ability to avoid punishment from early to late FP. Neither homozygote subjects of the 10RP allele, nor subjects from the HC group showed a change in behavior between phases. These data are consistent with neurobiological studies that found that rising E2 may reverse DA transporter function and could enhance DA efflux, which would in turn reduce punishment sensitivity particularly in subjects with a higher transporter density to begin with. Taken together, the present results, although based on a small sample, add to the growing understanding of the complex interplay between different physiological modulators of dopaminergic transmission. They may not only point out the necessity to control for hormonal state in behavioral genetic research, but may offer new starting points for studies in clinical settings.

  17. DAT1-Genotype and Menstrual Cycle, but Not Hormonal Contraception, Modulate Reinforcement Learning: Preliminary Evidence

    Directory of Open Access Journals (Sweden)

    Kristina Jakob

    2018-02-01

    Full Text Available Hormone by genotype interactions have been widely ignored by cognitive neuroscience. Yet, the dependence of cognitive performance on both baseline dopamine (DA and current 17ß-estradiol (E2 level argues for their combined effect also in the context of reinforcement learning. Here, we assessed how the interaction between the natural rise of E2 in the late follicular phase (FP and the 40 base-pair variable number tandem repeat polymorphism of the dopamine transporter (DAT1 affects reinforcement learning capacity. 30 women with a regular menstrual cycle performed a probabilistic feedback learning task twice during the early and late FP. In addition, 39 women, who took hormonal contraceptives (HC to suppress natural ovulation, were tested during the “pill break” and the intake phase of HC. The present data show that DAT1-genotype may interact with transient hormonal state, but only in women with a natural menstrual cycle. We found that carriers of the 9-repeat allele (9RP experienced a significant decrease in the ability to avoid punishment from early to late FP. Neither homozygote subjects of the 10RP allele, nor subjects from the HC group showed a change in behavior between phases. These data are consistent with neurobiological studies that found that rising E2 may reverse DA transporter function and could enhance DA efflux, which would in turn reduce punishment sensitivity particularly in subjects with a higher transporter density to begin with. Taken together, the present results, although based on a small sample, add to the growing understanding of the complex interplay between different physiological modulators of dopaminergic transmission. They may not only point out the necessity to control for hormonal state in behavioral genetic research, but may offer new starting points for studies in clinical settings.

  18. Long term effects of aversive reinforcement on colour discrimination learning in free-flying bumblebees.

    Directory of Open Access Journals (Sweden)

    Miguel A Rodríguez-Gironés

    Full Text Available The results of behavioural experiments provide important information about the structure and information-processing abilities of the visual system. Nevertheless, if we want to infer from behavioural data how the visual system operates, it is important to know how different learning protocols affect performance and to devise protocols that minimise noise in the response of experimental subjects. The purpose of this work was to investigate how reinforcement schedule and individual variability affect the learning process in a colour discrimination task. Free-flying bumblebees were trained to discriminate between two perceptually similar colours. The target colour was associated with sucrose solution, and the distractor could be associated with water or quinine solution throughout the experiment, or with one substance during the first half of the experiment and the other during the second half. Both acquisition and final performance of the discrimination task (measured as proportion of correct choices were determined by the choice of reinforcer during the first half of the experiment: regardless of whether bees were trained with water or quinine during the second half of the experiment, bees trained with quinine during the first half learned the task faster and performed better during the whole experiment. Our results confirm that the choice of stimuli used during training affects the rate at which colour discrimination tasks are acquired and show that early contact with a strongly aversive stimulus can be sufficient to maintain high levels of attention during several hours. On the other hand, bees which took more time to decide on which flower to alight were more likely to make correct choices than bees which made fast decisions. This result supports the existence of a trade-off between foraging speed and accuracy, and highlights the importance of measuring choice latencies during behavioural experiments focusing on cognitive abilities.

  19. Stochastic collusion and the power law of learning: a general reinforcement learning model of cooperation

    NARCIS (Netherlands)

    Flache, A.

    2002-01-01

    Concerns about models of cultural adaptation as analogs of genetic selection have led cognitive game theorists to explore learning-theoretic specifications. Two prominent examples, the Bush-Mosteller stochastic learning model and the Roth-Erev payoff-matching model, are aligned and integrated as

  20. Research and application of multi-agent genetic algorithm in tower defense game

    Science.gov (United States)

    Jin, Shaohua

    2018-04-01

    In this paper, a new multi-agent genetic algorithm based on orthogonal experiment is proposed, which is based on multi-agent system, genetic algorithm and orthogonal experimental design. The design of neighborhood competition operator, orthogonal crossover operator, Son and self-learning operator. The new algorithm is applied to mobile tower defense game, according to the characteristics of the game, the establishment of mathematical models, and finally increases the value of the game's monster.

  1. The "proactive" model of learning: Integrative framework for model-free and model-based reinforcement learning utilizing the associative learning-based proactive brain concept.

    Science.gov (United States)

    Zsuga, Judit; Biro, Klara; Papp, Csaba; Tajti, Gabor; Gesztelyi, Rudolf

    2016-02-01

    Reinforcement learning (RL) is a powerful concept underlying forms of associative learning governed by the use of a scalar reward signal, with learning taking place if expectations are violated. RL may be assessed using model-based and model-free approaches. Model-based reinforcement learning involves the amygdala, the hippocampus, and the orbitofrontal cortex (OFC). The model-free system involves the pedunculopontine-tegmental nucleus (PPTgN), the ventral tegmental area (VTA) and the ventral striatum (VS). Based on the functional connectivity of VS, model-free and model based RL systems center on the VS that by integrating model-free signals (received as reward prediction error) and model-based reward related input computes value. Using the concept of reinforcement learning agent we propose that the VS serves as the value function component of the RL agent. Regarding the model utilized for model-based computations we turned to the proactive brain concept, which offers an ubiquitous function for the default network based on its great functional overlap with contextual associative areas. Hence, by means of the default network the brain continuously organizes its environment into context frames enabling the formulation of analogy-based association that are turned into predictions of what to expect. The OFC integrates reward-related information into context frames upon computing reward expectation by compiling stimulus-reward and context-reward information offered by the amygdala and hippocampus, respectively. Furthermore we suggest that the integration of model-based expectations regarding reward into the value signal is further supported by the efferent of the OFC that reach structures canonical for model-free learning (e.g., the PPTgN, VTA, and VS). (c) 2016 APA, all rights reserved).

  2. Multi-agent sequential hypothesis testing

    KAUST Repository

    Kim, Kwang-Ki K.

    2014-12-15

    This paper considers multi-agent sequential hypothesis testing and presents a framework for strategic learning in sequential games with explicit consideration of both temporal and spatial coordination. The associated Bayes risk functions explicitly incorporate costs of taking private/public measurements, costs of time-difference and disagreement in actions of agents, and costs of false declaration/choices in the sequential hypothesis testing. The corresponding sequential decision processes have well-defined value functions with respect to (a) the belief states for the case of conditional independent private noisy measurements that are also assumed to be independent identically distributed over time, and (b) the information states for the case of correlated private noisy measurements. A sequential investment game of strategic coordination and delay is also discussed as an application of the proposed strategic learning rules.

  3. A Reinforcement Learning Approach to Call Admission Control in HAPS Communication System

    Directory of Open Access Journals (Sweden)

    Ni Shu Yan

    2017-01-01

    Full Text Available The large changing of link capacity and number of users caused by the movement of both platform and users in communication system based on high altitude platform station (HAPS will resulting in high dropping rate of handover and reduce resource utilization. In order to solve these problems, this paper proposes an adaptive call admission control strategy based on reinforcement learning approach. The goal of this strategy is to maximize long-term gains of system, with the introduction of cross-layer interaction and the service downgraded. In order to access different traffics adaptively, the access utility of handover traffics and new call traffics is designed in different state of communication system. Numerical simulation result shows that the proposed call admission control strategy can enhance bandwidth resource utilization and the performances of handover traffics.

  4. Understanding dopamine and reinforcement learning: the dopamine reward prediction error hypothesis.

    Science.gov (United States)

    Glimcher, Paul W

    2011-09-13

    A number of recent advances have been achieved in the study of midbrain dopaminergic neurons. Understanding these advances and how they relate to one another requires a deep understanding of the computational models that serve as an explanatory framework and guide ongoing experimental inquiry. This intertwining of theory and experiment now suggests very clearly that the phasic activity of the midbrain dopamine neurons provides a global mechanism for synaptic modification. These synaptic modifications, in turn, provide the mechanistic underpinning for a specific class of reinforcement learning mechanisms that now seem to underlie much of human and animal behavior. This review describes both the critical empirical findings that are at the root of this conclusion and the fantastic theoretical advances from which this conclusion is drawn.

  5. Off-Policy Reinforcement Learning: Optimal Operational Control for Two-Time-Scale Industrial Processes.

    Science.gov (United States)

    Li, Jinna; Kiumarsi, Bahare; Chai, Tianyou; Lewis, Frank L; Fan, Jialu

    2017-12-01

    Industrial flow lines are composed of unit processes operating on a fast time scale and performance measurements known as operational indices measured at a slower time scale. This paper presents a model-free optimal solution to a class of two time-scale industrial processes using off-policy reinforcement learning (RL). First, the lower-layer unit process control loop with a fast sampling period and the upper-layer operational index dynamics at a slow time scale are modeled. Second, a general optimal operational control problem is formulated to optimally prescribe the set-points for the unit industrial process. Then, a zero-sum game off-policy RL algorithm is developed to find the optimal set-points by using data measured in real-time. Finally, a simulation experiment is employed for an industrial flotation process to show the effectiveness of the proposed method.

  6. Reinforcement learning for adaptive optimal control of unknown continuous-time nonlinear systems with input constraints

    Science.gov (United States)

    Yang, Xiong; Liu, Derong; Wang, Ding

    2014-03-01

    In this paper, an adaptive reinforcement learning-based solution is developed for the infinite-horizon optimal control problem of constrained-input continuous-time nonlinear systems in the presence of nonlinearities with unknown structures. Two different types of neural networks (NNs) are employed to approximate the Hamilton-Jacobi-Bellman equation. That is, an recurrent NN is constructed to identify the unknown dynamical system, and two feedforward NNs are used as the actor and the critic to approximate the optimal control and the optimal cost, respectively. Based on this framework, the action NN and the critic NN are tuned simultaneously, without the requirement for the knowledge of system drift dynamics. Moreover, by using Lyapunov's direct method, the weights of the action NN and the critic NN are guaranteed to be uniformly ultimately bounded, while keeping the closed-loop system stable. To demonstrate the effectiveness of the present approach, simulation results are illustrated.

  7. A Reinforcement Learning Approach to Access Management in Wireless Cellular Networks

    Directory of Open Access Journals (Sweden)

    Jihun Moon

    2017-01-01

    Full Text Available In smart city applications, huge numbers of devices need to be connected in an autonomous manner. 3rd Generation Partnership Project (3GPP specifies that Machine Type Communication (MTC should be used to handle data transmission among a large number of devices. However, the data transmission rates are highly variable, and this brings about a congestion problem. To tackle this problem, the use of Access Class Barring (ACB is recommended to restrict the number of access attempts allowed in data transmission by utilizing strategic parameters. In this paper, we model the problem of determining the strategic parameters with a reinforcement learning algorithm. In our model, the system evolves to minimize both the collision rate and the access delay. The experimental results show that our scheme improves system performance in terms of the access success rate, the failure rate, the collision rate, and the access delay.

  8. From free energy to expected energy: Improving energy-based value function approximation in reinforcement learning.

    Science.gov (United States)

    Elfwing, Stefan; Uchibe, Eiji; Doya, Kenji

    2016-12-01

    Free-energy based reinforcement learning (FERL) was proposed for learning in high-dimensional state and action spaces. However, the FERL method does only really work well with binary, or close to binary, state input, where the number of active states is fewer than the number of non-active states. In the FERL method, the value function is approximated by the negative free energy of a restricted Boltzmann machine (RBM). In our earlier study, we demonstrated that the performance and the robustness of the FERL method can be improved by scaling the free energy by a constant that is related to the size of network. In this study, we propose that RBM function approximation can be further improved by approximating the value function by the negative expected energy (EERL), instead of the negative free energy, as well as being able to handle continuous state input. We validate our proposed method by demonstrating that EERL: (1) outperforms FERL, as well as standard neural network and linear function approximation, for three versions of a gridworld task with high-dimensional image state input; (2) achieves new state-of-the-art results in stochastic SZ-Tetris in both model-free and model-based learning settings; and (3) significantly outperforms FERL and standard neural network function approximation for a robot navigation task with raw and noisy RGB images as state input and a large number of actions. Copyright © 2016 The Author(s). Published by Elsevier Ltd.. All rights reserved.

  9. Continuous theta-burst stimulation (cTBS) over the lateral prefrontal cortex alters reinforcement learning bias

    NARCIS (Netherlands)

    Ott, D.V.M.; Ullsperger, M.; Jocham, G.; Neumann, J.; Klein, T.A.

    2011-01-01

    The prefrontal cortex is known to play a key role in higher-order cognitive functions. Recently, we showed that this brain region is active in reinforcement learning, during which subjects constantly have to integrate trial outcomes in order to optimize performance. To further elucidate the role of

  10. Using Spatial Reinforcement Learning to Build Forest Wildfire Dynamics Models From Satellite Images

    Directory of Open Access Journals (Sweden)

    Sriram Ganapathi Subramanian

    2018-04-01

    Full Text Available Machine learning algorithms have increased tremendously in power in recent years but have yet to be fully utilized in many ecology and sustainable resource management domains such as wildlife reserve design, forest fire management, and invasive species spread. One thing these domains have in common is that they contain dynamics that can be characterized as a spatially spreading process (SSP, which requires many parameters to be set precisely to model the dynamics, spread rates, and directional biases of the elements which are spreading. We present related work in artificial intelligence and machine learning for SSP sustainability domains including forest wildfire prediction. We then introduce a novel approach for learning in SSP domains using reinforcement learning (RL where fire is the agent at any cell in the landscape and the set of actions the fire can take from a location at any point in time includes spreading north, south, east, or west or not spreading. This approach inverts the usual RL setup since the dynamics of the corresponding Markov Decision Process (MDP is a known function for immediate wildfire spread. Meanwhile, we learn an agent policy for a predictive model of the dynamics of a complex spatial process. Rewards are provided for correctly classifying which cells are on fire or not compared with satellite and other related data. We examine the behavior of five RL algorithms on this problem: value iteration, policy iteration, Q-learning, Monte Carlo Tree Search, and Asynchronous Advantage Actor-Critic (A3C. We compare to a Gaussian process-based supervised learning approach and also discuss the relation of our approach to manually constructed, state-of-the-art methods from forest wildfire modeling. We validate our approach with satellite image data of two massive wildfire events in Northern Alberta, Canada; the Fort McMurray fire of 2016 and the Richardson fire of 2011. The results show that we can learn predictive, agent

  11. Spike-based decision learning of Nash equilibria in two-player games.

    Directory of Open Access Journals (Sweden)

    Johannes Friedrich

    Full Text Available Humans and animals face decision tasks in an uncertain multi-agent environment where an agent's strategy may change in time due to the co-adaptation of others strategies. The neuronal substrate and the computational algorithms underlying such adaptive decision making, however, is largely unknown. We propose a population coding model of spiking neurons with a policy gradient procedure that successfully acquires optimal strategies for classical game-theoretical tasks. The suggested population reinforcement learning reproduces data from human behavioral experiments for the blackjack and the inspector game. It performs optimally according to a pure (deterministic and mixed (stochastic Nash equilibrium, respectively. In contrast, temporal-difference(TD-learning, covariance-learning, and basic reinforcement learning fail to perform optimally for the stochastic strategy. Spike-based population reinforcement learning, shown to follow the stochastic reward gradient, is therefore a viable candidate to explain automated decision learning of a Nash equilibrium in two-player games.

  12. Examining Organizational Learning in Schools: The Role of Psychological Safety, Experimentation, and Leadership that Reinforces Learning

    Science.gov (United States)

    Higgins, Monica; Ishimaru, Ann; Holcombe, Rebecca; Fowler, Amy

    2012-01-01

    This study draws upon theory and methods from the field of organizational behavior to examine organizational learning (OL) in the context of a large urban US school district. We build upon prior literature on OL from the field of organizational behavior to introduce and validate three subscales that assess key dimensions of organizational learning…

  13. Learning Multirobot Hose Transportation and Deployment by Distributed Round-Robin Q-Learning.

    Directory of Open Access Journals (Sweden)

    Borja Fernandez-Gauna

    Full Text Available Multi-Agent Reinforcement Learning (MARL algorithms face two main difficulties: the curse of dimensionality, and environment non-stationarity due to the independent learning processes carried out by the agents concurrently. In this paper we formalize and prove the convergence of a Distributed Round Robin Q-learning (D-RR-QL algorithm for cooperative systems. The computational complexity of this algorithm increases linearly with the number of agents. Moreover, it eliminates environment non sta tionarity by carrying a round-robin scheduling of the action selection and execution. That this learning scheme allows the implementation of Modular State-Action Vetoes (MSAV in cooperative multi-agent systems, which speeds up learning convergence in over-constrained systems by vetoing state-action pairs which lead to undesired termination states (UTS in the relevant state-action subspace. Each agent's local state-action value function learning is an independent process, including the MSAV policies. Coordination of locally optimal policies to obtain the global optimal joint policy is achieved by a greedy selection procedure using message passing. We show that D-RR-QL improves over state-of-the-art approaches, such as Distributed Q-Learning, Team Q-Learning and Coordinated Reinforcement Learning in a paradigmatic Linked Multi-Component Robotic System (L-MCRS control problem: the hose transportation task. L-MCRS are over-constrained systems with many UTS induced by the interaction of the passive linking element and the active mobile robots.

  14. 14th International Conference on Practical Applications of Agents and Multi-Agent Systems : Special Sessions

    CERN Document Server

    Escalona, María; Corchuelo, Rafael; Mathieu, Philippe; Vale, Zita; Campbell, Andrew; Rossi, Silvia; Adam, Emmanuel; Jiménez-López, María; Navarro, Elena; Moreno, María

    2016-01-01

    PAAMS, the International Conference on Practical Applications of Agents and Multi-Agent Systems is an evolution of the International Workshop on Practical Applications of Agents and Multi-Agent Systems. PAAMS is an international yearly tribune to present, to discuss, and to disseminate the latest developments and the most important outcomes related to real-world applications. It provides a unique opportunity to bring multi-disciplinary experts, academics and practitioners together to exchange their experience in the development of Agents and Multi-Agent Systems. This volume presents the papers that have been accepted for the 2016 in the special sessions: Agents Behaviours and Artificial Markets (ABAM); Advances on Demand Response and Renewable Energy Sources in Agent Based Smart Grids (ADRESS); Agents and Mobile Devices (AM); Agent Methodologies for Intelligent Robotics Applications (AMIRA); Learning, Agents and Formal Languages (LAFLang); Multi-Agent Systems and Ambient Intelligence (MASMAI); Web Mining and ...

  15. Multiage Assessment: One School's Plan.

    Science.gov (United States)

    Arnold, Sue Beth; Kidwell, Barbara; Rossman, David

    1998-01-01

    Describes one elementary school's multiage assessment plan. Describes how standards were developed, and describes the assessment plan's guiding element: the progress report arranged as a continuum of objectives that serve as a goal indicator and a reporting mechanism. Discusses how objectives are assessed, record keeping and documentation, and the…

  16. Enhanced risk management by an emerging multi-agent architecture

    Science.gov (United States)

    Lin, Sin-Jin; Hsu, Ming-Fu

    2014-07-01

    Classification in imbalanced datasets has attracted much attention from researchers in the field of machine learning. Most existing techniques tend not to perform well on minority class instances when the dataset is highly skewed because they focus on minimising the forecasting error without considering the relative distribution of each class. This investigation proposes an emerging multi-agent architecture, grounded on cooperative learning, to solve the class-imbalanced classification problem. Additionally, this study deals further with the obscure nature of the multi-agent architecture and expresses comprehensive rules for auditors. The results from this study indicate that the presented model performs satisfactorily in risk management and is able to tackle a highly class-imbalanced dataset comparatively well. Furthermore, the knowledge visualised process, supported by real examples, can assist both internal and external auditors who must allocate limited detecting resources; they can take the rules as roadmaps to modify the auditing programme.

  17. Application of Reinforcement Learning in Cognitive Radio Networks: Models and Algorithms

    Directory of Open Access Journals (Sweden)

    Kok-Lim Alvin Yau

    2014-01-01

    Full Text Available Cognitive radio (CR enables unlicensed users to exploit the underutilized spectrum in licensed spectrum whilst minimizing interference to licensed users. Reinforcement learning (RL, which is an artificial intelligence approach, has been applied to enable each unlicensed user to observe and carry out optimal actions for performance enhancement in a wide range of schemes in CR, such as dynamic channel selection and channel sensing. This paper presents new discussions of RL in the context of CR networks. It provides an extensive review on how most schemes have been approached using the traditional and enhanced RL algorithms through state, action, and reward representations. Examples of the enhancements on RL, which do not appear in the traditional RL approach, are rules and cooperative learning. This paper also reviews performance enhancements brought about by the RL algorithms and open issues. This paper aims to establish a foundation in order to spark new research interests in this area. Our discussion has been presented in a tutorial manner so that it is comprehensive to readers outside the specialty of RL and CR.

  18. Pareto Optimal Solutions for Network Defense Strategy Selection Simulator in Multi-Objective Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Yang Sun

    2018-01-01

    Full Text Available Using Pareto optimization in Multi-Objective Reinforcement Learning (MORL leads to better learning results for network defense games. This is particularly useful for network security agents, who must often balance several goals when choosing what action to take in defense of a network. If the defender knows his preferred reward distribution, the advantages of Pareto optimization can be retained by using a scalarization algorithm prior to the implementation of the MORL. In this paper, we simulate a network defense scenario by creating a multi-objective zero-sum game and using Pareto optimization and MORL to determine optimal solutions and compare those solutions to different scalarization approaches. We build a Pareto Defense Strategy Selection Simulator (PDSSS system for assisting network administrators on decision-making, specifically, on defense strategy selection, and the experiment results show that the Satisficing Trade-Off Method (STOM scalarization approach performs better than linear scalarization or GUESS method. The results of this paper can aid network security agents attempting to find an optimal defense policy for network security games.

  19. CAPES: Unsupervised Storage Performance Tuning Using Neural Network-Based Deep Reinforcement Learning

    CERN Multimedia

    CERN. Geneva

    2017-01-01

    Parameter tuning is an important task of storage performance optimization. Current practice usually involves numerous tweak-benchmark cycles that are slow and costly. To address this issue, we developed CAPES, a model-less deep reinforcement learning-based unsupervised parameter tuning system driven by a deep neural network (DNN). It is designed to nd the optimal values of tunable parameters in computer systems, from a simple client-server system to a large data center, where human tuning can be costly and often cannot achieve optimal performance. CAPES takes periodic measurements of a target computer system’s state, and trains a DNN which uses Q-learning to suggest changes to the system’s current parameter values. CAPES is minimally intrusive, and can be deployed into a production system to collect training data and suggest tuning actions during the system’s daily operation. Evaluation of a prototype on a Lustre system demonstrates an increase in I/O throughput up to 45% at saturation point. About the...

  20. Toward an autonomous brain machine interface: integrating sensorimotor reward modulation and reinforcement learning.

    Science.gov (United States)

    Marsh, Brandi T; Tarigoppula, Venkata S Aditya; Chen, Chen; Francis, Joseph T

    2015-05-13

    For decades, neurophysiologists have worked on elucidating the function of the cortical sensorimotor control system from the standpoint of kinematics or dynamics. Recently, computational neuroscientists have developed models that can emulate changes seen in the primary motor cortex during learning. However, these simulations rely on the existence of a reward-like signal in the primary sensorimotor cortex. Reward modulation of the primary sensorimotor cortex has yet to be characterized at the level of neural units. Here we demonstrate that single units/multiunits and local field potentials in the primary motor (M1) cortex of nonhuman primates (Macaca radiata) are modulated by reward expectation during reaching movements and that this modulation is present even while subjects passively view cursor motions that are predictive of either reward or nonreward. After establishing this reward modulation, we set out to determine whether we could correctly classify rewarding versus nonrewarding trials, on a moment-to-moment basis. This reward information could then be used in collaboration with reinforcement learning principles toward an autonomous brain-machine interface. The autonomous brain-machine interface would use M1 for both decoding movement intention and extraction of reward expectation information as evaluative feedback, which would then update the decoding algorithm as necessary. In the work presented here, we show that this, in theory, is possible. Copyright © 2015 the authors 0270-6474/15/357374-14$15.00/0.

  1. Classification of amyotrophic lateral sclerosis disease based on convolutional neural network and reinforcement sample learning algorithm.

    Science.gov (United States)

    Sengur, Abdulkadir; Akbulut, Yaman; Guo, Yanhui; Bajaj, Varun

    2017-12-01

    Electromyogram (EMG) signals contain useful information of the neuromuscular diseases like amyotrophic lateral sclerosis (ALS). ALS is a well-known brain disease, which can progressively degenerate the motor neurons. In this paper, we propose a deep learning based method for efficient classification of ALS and normal EMG signals. Spectrogram, continuous wavelet transform (CWT), and smoothed pseudo Wigner-Ville distribution (SPWVD) have been employed for time-frequency (T-F) representation of EMG signals. A convolutional neural network is employed to classify these features. In it, Two convolution layers, two pooling layer, a fully connected layer and a lost function layer is considered in CNN architecture. The CNN architecture is trained with the reinforcement sample learning strategy. The efficiency of the proposed implementation is tested on publicly available EMG dataset. The dataset contains 89 ALS and 133 normal EMG signals with 24 kHz sampling frequency. Experimental results show 96.80% accuracy. The obtained results are also compared with other methods, which show the superiority of the proposed method.

  2. Learning Agent for a Heat-Pump Thermostat with a Set-Back Strategy Using Model-Free Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Frederik Ruelens

    2015-08-01

    Full Text Available The conventional control paradigm for a heat pump with a less efficient auxiliary heating element is to keep its temperature set point constant during the day. This constant temperature set point ensures that the heat pump operates in its more efficient heat-pump mode and minimizes the risk of activating the less efficient auxiliary heating element. As an alternative to a constant set-point strategy, this paper proposes a learning agent for a thermostat with a set-back strategy. This set-back strategy relaxes the set-point temperature during convenient moments, e.g., when the occupants are not at home. Finding an optimal set-back strategy requires solving a sequential decision-making process under uncertainty, which presents two challenges. The first challenge is that for most residential buildings, a description of the thermal characteristics of the building is unavailable and challenging to obtain. The second challenge is that the relevant information on the state, i.e., the building envelope, cannot be measured by the learning agent. In order to overcome these two challenges, our paper proposes an auto-encoder coupled with a batch reinforcement learning technique. The proposed approach is validated for two building types with different thermal characteristics for heating in the winter and cooling in the summer. The simulation results indicate that the proposed learning agent can reduce the energy consumption by 4%–9% during 100 winter days and by 9%–11% during 80 summer days compared to the conventional constant set-point strategy.

  3. Reinforcement learning modulates the stability of cognitive control settings for object selection

    Directory of Open Access Journals (Sweden)

    Anthony William Sali

    2013-12-01

    Full Text Available Cognitive flexibility reflects both a trait that reliably differs between individuals and a state that can fluctuate moment-to-moment. Whether individuals can undergo persistent changes in cognitive flexibility as a result of reward learning is less understood. Here, we investigated whether reinforcing a periodic shift in an object selection strategy can make an individual more prone to switch strategies in a subsequent unrelated task. Participants completed two different choice tasks in which they selected one of four objects in an attempt to obtain a hidden reward on each trial. During a training phase, objects were defined by color. Participants received either consistent reward contingencies in which one color was more often rewarded, or contingencies in which the color that was more often rewarded changed periodically and without warning. Following the training phase, all participants completed a test phase in which reward contingencies were defined by spatial location and the location that was more often rewarded remained constant across the entire task. Those participants who received inconsistent contingencies during training continued to make more variable selections during the test phase in comparison to those who received the consistent training. Furthermore, a difference in the likelihood to switch selections on a trial-by-trial basis emerged between training groups: participants who received consistent contingencies during training were less likely to switch object selections following an unrewarded trial and more likely to repeat a selection following reward. Our findings provide evidence that the extent to which priority shifting is reinforced modulates the stability of cognitive control settings in a persistent manner, such that individuals become generally more or less prone to shifting priorities in the future.

  4. Predicting Pilot Behavior in Medium Scale Scenarios Using Game Theory and Reinforcement Learning

    Science.gov (United States)

    Yildiz, Yildiray; Agogino, Adrian; Brat, Guillaume

    2013-01-01

    Effective automation is critical in achieving the capacity and safety goals of the Next Generation Air Traffic System. Unfortunately creating integration and validation tools for such automation is difficult as the interactions between automation and their human counterparts is complex and unpredictable. This validation becomes even more difficult as we integrate wide-reaching technologies that affect the behavior of different decision makers in the system such as pilots, controllers and airlines. While overt short-term behavior changes can be explicitly modeled with traditional agent modeling systems, subtle behavior changes caused by the integration of new technologies may snowball into larger problems and be very hard to detect. To overcome these obstacles, we show how integration of new technologies can be validated by learning behavior models based on goals. In this framework, human participants are not modeled explicitly. Instead, their goals are modeled and through reinforcement learning their actions are predicted. The main advantage to this approach is that modeling is done within the context of the entire system allowing for accurate modeling of all participants as they interact as a whole. In addition such an approach allows for efficient trade studies and feasibility testing on a wide range of automation scenarios. The goal of this paper is to test that such an approach is feasible. To do this we implement this approach using a simple discrete-state learning system on a scenario where 50 aircraft need to self-navigate using Automatic Dependent Surveillance-Broadcast (ADS-B) information. In this scenario, we show how the approach can be used to predict the ability of pilots to adequately balance aircraft separation and fly efficient paths. We present results with several levels of complexity and airspace congestion.

  5. Reinforcement learning signals in the human striatum distinguish learners from nonlearners during reward-based decision making.

    Science.gov (United States)

    Schönberg, Tom; Daw, Nathaniel D; Joel, Daphna; O'Doherty, John P

    2007-11-21

    The computational framework of reinforcement learning has been used to forward our understanding of the neural mechanisms underlying reward learning and decision-making behavior. It is known that humans vary widely in their performance in decision-making tasks. Here, we used a simple four-armed bandit task in which subjects are almost evenly split into two groups on the basis of their performance: those who do learn to favor choice of the optimal action and those who do not. Using models of reinforcement learning we sought to determine the neural basis of these intrinsic differences in performance by scanning both groups with functional magnetic resonance imaging. We scanned 29 subjects while they performed the reward-based decision-making task. Our results suggest that these two groups differ markedly in the degree to which reinforcement learning signals in the striatum are engaged during task performance. While the learners showed robust prediction error signals in both the ventral and dorsal striatum during learning, the nonlearner group showed a marked absence of such signals. Moreover, the magnitude of prediction error signals in a region of dorsal striatum correlated significantly with a measure of behavioral performance across all subjects. These findings support a crucial role of prediction error signals, likely originating from dopaminergic midbrain neurons, in enabling learning of action selection preferences on the basis of obtained rewards. Thus, spontaneously observed individual differences in decision making performance demonstrate the suggested dependence of this type of learning on the functional integrity of the dopaminergic striatal system in humans.

  6. Medial prefrontal cortex and the adaptive regulation of reinforcement learning parameters.

    Science.gov (United States)

    Khamassi, Mehdi; Enel, Pierre; Dominey, Peter Ford; Procyk, Emmanuel

    2013-01-01

    Converging evidence suggest that the medial prefrontal cortex (MPFC) is involved in feedback categorization, performance monitoring, and task monitoring, and may contribute to the online regulation of reinforcement learning (RL) parameters that would affect decision-making processes in the lateral prefrontal cortex (LPFC). Previous neurophysiological experiments have shown MPFC activities encoding error likelihood, uncertainty, reward volatility, as well as neural responses categorizing different types of feedback, for instance, distinguishing between choice errors and execution errors. Rushworth and colleagues have proposed that the involvement of MPFC in tracking the volatility of the task could contribute to the regulation of one of RL parameters called the learning rate. We extend this hypothesis by proposing that MPFC could contribute to the regulation of other RL parameters such as the exploration rate and default action values in case of task shifts. Here, we analyze the sensitivity to RL parameters of behavioral performance in two monkey decision-making tasks, one with a deterministic reward schedule and the other with a stochastic one. We show that there exist optimal parameter values specific to each of these tasks, that need to be found for optimal performance and that are usually hand-tuned in computational models. In contrast, automatic online regulation of these parameters using some heuristics can help producing a good, although non-optimal, behavioral performance in each task. We finally describe our computational model of MPFC-LPFC interaction used for online regulation of the exploration rate and its application to a human-robot interaction scenario. There, unexpected uncertainties are produced by the human introducing cued task changes or by cheating. The model enables the robot to autonomously learn to reset exploration in response to such uncertain cues and events. The combined results provide concrete evidence specifying how prefrontal

  7. Neural Control of a Tracking Task via Attention-Gated Reinforcement Learning for Brain-Machine Interfaces.

    Science.gov (United States)

    Wang, Yiwen; Wang, Fang; Xu, Kai; Zhang, Qiaosheng; Zhang, Shaomin; Zheng, Xiaoxiang

    2015-05-01

    Reinforcement learning (RL)-based brain machine interfaces (BMIs) enable the user to learn from the environment through interactions to complete the task without desired signals, which is promising for clinical applications. Previous studies exploited Q-learning techniques to discriminate neural states into simple directional actions providing the trial initial timing. However, the movements in BMI applications can be quite complicated, and the action timing explicitly shows the intention when to move. The rich actions and the corresponding neural states form a large state-action space, imposing generalization difficulty on Q-learning. In this paper, we propose to adopt attention-gated reinforcement learning (AGREL) as a new learning scheme for BMIs to adaptively decode high-dimensional neural activities into seven distinct movements (directional moves, holdings and resting) due to the efficient weight-updating. We apply AGREL on neural data recorded from M1 of a monkey to directly predict a seven-action set in a time sequence to reconstruct the trajectory of a center-out task. Compared to Q-learning techniques, AGREL could improve the target acquisition rate to 90.16% in average with faster convergence and more stability to follow neural activity over multiple days, indicating the potential to achieve better online decoding performance for more complicated BMI tasks.

  8. Multiagent path-finding in strategic games

    OpenAIRE

    Mihevc, Simon

    2014-01-01

    In this thesis I worked on creating, comparing and improving algorithms for multi-agent path planning on a domain typical for real-time strategy games. I implemented and compared Multiagent pathfinding using clearance and Multiagent pathfinding using independence detection and operator decomposition. I discovered that they had problems maintaining group compactness and took too long to calculate the path. I considerably improved the efficiency of both algorithms.

  9. Does temporal discounting explain unhealthy behavior? A systematic review and reinforcement learning perspective

    Science.gov (United States)

    Story, Giles W.; Vlaev, Ivo; Seymour, Ben; Darzi, Ara; Dolan, Raymond J.

    2014-01-01

    The tendency to make unhealthy choices is hypothesized to be related to an individual's temporal discount rate, the theoretical rate at which they devalue delayed rewards. Furthermore, a particular form of temporal discounting, hyperbolic discounting, has been proposed to explain why unhealthy behavior can occur despite healthy intentions. We examine these two hypotheses in turn. We first systematically review studies which investigate whether discount rates can predict unhealthy behavior. These studies reveal that high discount rates for money (and in some instances food or drug rewards) are associated with several unhealthy behaviors and markers of health status, establishing discounting as a promising predictive measure. We secondly examine whether intention-incongruent unhealthy actions are consistent with hyperbolic discounting. We conclude that intention-incongruent actions are often triggered by environmental cues or changes in motivational state, whose effects are not parameterized by hyperbolic discounting. We propose a framework for understanding these state-based effects in terms of the interplay of two distinct reinforcement learning mechanisms: a “model-based” (or goal-directed) system and a “model-free” (or habitual) system. Under this framework, while discounting of delayed health may contribute to the initiation of unhealthy behavior, with repetition, many unhealthy behaviors become habitual; if health goals then change, habitual behavior can still arise in response to environmental cues. We propose that the burgeoning development of computational models of these processes will permit further identification of health decision-making phenotypes. PMID:24659960

  10. Extending the Peak Bandwidth of Parameters for Softmax Selection in Reinforcement Learning.

    Science.gov (United States)

    Iwata, Kazunori

    2016-05-11

    Softmax selection is one of the most popular methods for action selection in reinforcement learning. Although various recently proposed methods may be more effective with full parameter tuning, implementing a complicated method that requires the tuning of many parameters can be difficult. Thus, softmax selection is still worth revisiting, considering the cost savings of its implementation and tuning. In fact, this method works adequately in practice with only one parameter appropriately set for the environment. The aim of this paper is to improve the variable setting of this method to extend the bandwidth of good parameters, thereby reducing the cost of implementation and parameter tuning. To achieve this, we take advantage of the asymptotic equipartition property in a Markov decision process to extend the peak bandwidth of softmax selection. Using a variety of episodic tasks, we show that our setting is effective in extending the bandwidth and that it yields a better policy in terms of stability. The bandwidth is quantitatively assessed in a series of statistical tests.

  11. Distribution majorization of corner points by reinforcement learning for moving object detection

    Science.gov (United States)

    Wu, Hao; Yu, Hao; Zhou, Dongxiang; Cheng, Yongqiang

    2018-04-01

    Corner points play an important role in moving object detection, especially in the case of free-moving camera. Corner points provide more accurate information than other pixels and reduce the computation which is unnecessary. Previous works only use intensity information to locate the corner points, however, the information that former and the last frames provided also can be used. We utilize the information to focus on more valuable area and ignore the invaluable area. The proposed algorithm is based on reinforcement learning, which regards the detection of corner points as a Markov process. In the Markov model, the video to be detected is regarded as environment, the selections of blocks for one corner point are regarded as actions and the performance of detection is regarded as state. Corner points are assigned to be the blocks which are seperated from original whole image. Experimentally, we select a conventional method which uses marching and Random Sample Consensus algorithm to obtain objects as the main framework and utilize our algorithm to improve the result. The comparison between the conventional method and the same one with our algorithm show that our algorithm reduce 70% of the false detection.

  12. Elevator Group Supervisory Control System Using Genetic Network Programming with Macro Nodes and Reinforcement Learning

    Science.gov (United States)

    Zhou, Jin; Yu, Lu; Mabu, Shingo; Hirasawa, Kotaro; Hu, Jinglu; Markon, Sandor

    Elevator Group Supervisory Control System (EGSCS) is a very large scale stochastic dynamic optimization problem. Due to its vast state space, significant uncertainty and numerous resource constraints such as finite car capacities and registered hall/car calls, it is hard to manage EGSCS using conventional control methods. Recently, many solutions for EGSCS using Artificial Intelligence (AI) technologies have been reported. Genetic Network Programming (GNP), which is proposed as a new evolutionary computation method several years ago, is also proved to be efficient when applied to EGSCS problem. In this paper, we propose an extended algorithm for EGSCS by introducing Reinforcement Learning (RL) into GNP framework, and an improvement of the EGSCS' performances is expected since the efficiency of GNP with RL has been clarified in some other studies like tile-world problem. Simulation tests using traffic flows in a typical office building have been made, and the results show an actual improvement of the EGSCS' performances comparing to the algorithms using original GNP and conventional control methods. Furthermore, as a further study, an importance weight optimization algorithm is employed based on GNP with RL and its efficiency is also verified with the better performances.

  13. Distinguishing between learning and motivation in behavioral tests of the reinforcement sensitivity theory of personality.

    Science.gov (United States)

    Smillie, Luke D; Dalgleish, Len I; Jackson, Chris J

    2007-04-01

    According to Gray's (1973) Reinforcement Sensitivity Theory (RST), a Behavioral Inhibition System (BIS) and a Behavioral Activation System (BAS) mediate effects of goal conflict and reward on behavior. BIS functioning has been linked with individual differences in trait anxiety and BAS functioning with individual differences in trait impulsivity. In this article, it is argued that behavioral outputs of the BIS and BAS can be distinguished in terms of learning and motivation processes and that these can be operationalized using the Signal Detection Theory measures of response-sensitivity and response-bias. In Experiment 1, two measures of BIS-reactivity predicted increased response-sensitivity under goal conflict, whereas one measure of BAS-reactivity predicted increased response-sensitivity under reward. In Experiment 2, two measures of BIS-reactivity predicted response-bias under goal conflict, whereas a measure of BAS-reactivity predicted motivation response-bias under reward. In both experiments, impulsivity measures did not predict criteria for BAS-reactivity as traditionally predicted by RST.

  14. A Novel Dynamic Spectrum Access Framework Based on Reinforcement Learning for Cognitive Radio Sensor Networks

    Directory of Open Access Journals (Sweden)

    Yun Lin

    2016-10-01

    Full Text Available Cognitive radio sensor networks are one of the kinds of application where cognitive techniques can be adopted and have many potential applications, challenges and future research trends. According to the research surveys, dynamic spectrum access is an important and necessary technology for future cognitive sensor networks. Traditional methods of dynamic spectrum access are based on spectrum holes and they have some drawbacks, such as low accessibility and high interruptibility, which negatively affect the transmission performance of the sensor networks. To address this problem, in this paper a new initialization mechanism is proposed to establish a communication link and set up a sensor network without adopting spectrum holes to convey control information. Specifically, firstly a transmission channel model for analyzing the maximum accessible capacity for three different polices in a fading environment is discussed. Secondly, a hybrid spectrum access algorithm based on a reinforcement learning model is proposed for the power allocation problem of both the transmission channel and the control channel. Finally, extensive simulations have been conducted and simulation results show that this new algorithm provides a significant improvement in terms of the tradeoff between the control channel reliability and the efficiency of the transmission channel.

  15. Trading Rules on Stock Markets Using Genetic Network Programming with Reinforcement Learning and Importance Index

    Science.gov (United States)

    Mabu, Shingo; Hirasawa, Kotaro; Furuzuki, Takayuki

    Genetic Network Programming (GNP) is an evolutionary computation which represents its solutions using graph structures. Since GNP can create quite compact programs and has an implicit memory function, it has been clarified that GNP works well especially in dynamic environments. In addition, a study on creating trading rules on stock markets using GNP with Importance Index (GNP-IMX) has been done. IMX is a new element which is a criterion for decision making. In this paper, we combined GNP-IMX with Actor-Critic (GNP-IMX&AC) and create trading rules on stock markets. Evolution-based methods evolve their programs after enough period of time because they must calculate fitness values, however reinforcement learning can change programs during the period, therefore the trading rules can be created efficiently. In the simulation, the proposed method is trained using the stock prices of 10 brands in 2002 and 2003. Then the generalization ability is tested using the stock prices in 2004. The simulation results show that the proposed method can obtain larger profits than GNP-IMX without AC and Buy&Hold.

  16. Reinforcement learning controller design for affine nonlinear discrete-time systems using online approximators.

    Science.gov (United States)

    Yang, Qinmin; Jagannathan, Sarangapani

    2012-04-01

    In this paper, reinforcement learning state- and output-feedback-based adaptive critic controller designs are proposed by using the online approximators (OLAs) for a general multi-input and multioutput affine unknown nonlinear discretetime systems in the presence of bounded disturbances. The proposed controller design has two entities, an action network that is designed to produce optimal signal and a critic network that evaluates the performance of the action network. The critic estimates the cost-to-go function which is tuned online using recursive equations derived from heuristic dynamic programming. Here, neural networks (NNs) are used both for the action and critic whereas any OLAs, such as radial basis functions, splines, fuzzy logic, etc., can be utilized. For the output-feedback counterpart, an additional NN is designated as the observer to estimate the unavailable system states, and thus, separation principle is not required. The NN weight tuning laws for the controller schemes are also derived while ensuring uniform ultimate boundedness of the closed-loop system using Lyapunov theory. Finally, the effectiveness of the two controllers is tested in simulation on a pendulum balancing system and a two-link robotic arm system.

  17. Aversive reinforcement improves visual discrimination learning in free-flying honeybees.

    Directory of Open Access Journals (Sweden)

    Aurore Avarguès-Weber

    Full Text Available BACKGROUND: Learning and perception of visual stimuli by free-flying honeybees has been shown to vary dramatically depending on the way insects are trained. Fine color discrimination is achieved when both a target and a distractor are present during training (differential conditioning, whilst if the same target is learnt in isolation (absolute conditioning, discrimination is coarse and limited to perceptually dissimilar alternatives. Another way to potentially enhance discrimination is to increase the penalty associated with the distractor. Here we studied whether coupling the distractor with a highly concentrated quinine solution improves color discrimination of both similar and dissimilar colors by free-flying honeybees. As we assumed that quinine acts as an aversive stimulus, we analyzed whether aversion, if any, is based on an aversive sensory input at the gustatory level or on a post-ingestional malaise following quinine feeding. METHODOLOGY/PRINCIPAL FINDINGS: We show that the presence of a highly concentrated quinine solution (60 mM acts as an aversive reinforcer promoting rejection of the target associated with it, and improving discrimination of perceptually similar stimuli but not of dissimilar stimuli. Free-flying bees did not use remote cues to detect the presence of quinine solution; the aversive effect exerted by this substance was mediated via a gustatory input, i.e. via a distasteful sensory experience, rather than via a post-ingestional malaise. CONCLUSION: The present study supports the hypothesis that aversion conditioning is important for understanding how and what animals perceive and learn. By using this form of conditioning coupled with appetitive conditioning in the framework of a differential conditioning procedure, it is possible to uncover discrimination capabilities that may remain otherwise unsuspected. We show, therefore, that visual discrimination is not an absolute phenomenon but can be modulated by experience.

  18. Corticostriatal circuit mechanisms of value-based action selection: Implementation of reinforcement learning algorithms and beyond.

    Science.gov (United States)

    Morita, Kenji; Jitsev, Jenia; Morrison, Abigail

    2016-09-15

    Value-based action selection has been suggested to be realized in the corticostriatal local circuits through competition among neural populations. In this article, we review theoretical and experimental studies that have constructed and verified this notion, and provide new perspectives on how the local-circuit selection mechanisms implement reinforcement learning (RL) algorithms and computations beyond them. The striatal neurons are mostly inhibitory, and lateral inhibition among them has been classically proposed to realize "Winner-Take-All (WTA)" selection of the maximum-valued action (i.e., 'max' operation). Although this view has been challenged by the revealed weakness, sparseness, and asymmetry of lateral inhibition, which suggest more complex dynamics, WTA-like competition could still occur on short time scales. Unlike the striatal circuit, the cortical circuit contains recurrent excitation, which may enable retention or temporal integration of information and probabilistic "soft-max" selection. The striatal "max" circuit and the cortical "soft-max" circuit might co-implement an RL algorithm called Q-learning; the cortical circuit might also similarly serve for other algorithms such as SARSA. In these implementations, the cortical circuit presumably sustains activity representing the executed action, which negatively impacts dopamine neurons so that they can calculate reward-prediction-error. Regarding the suggested more complex dynamics of striatal, as well as cortical, circuits on long time scales, which could be viewed as a sequence of short WTA fragments, computational roles remain open: such a sequence might represent (1) sequential state-action-state transitions, constituting replay or simulation of the internal model, (2) a single state/action by the whole trajectory, or (3) probabilistic sampling of state/action. Copyright © 2016. Published by Elsevier B.V.

  19. Implementation of real-time energy management strategy based on reinforcement learning for hybrid electric vehicles and simulation validation.

    Directory of Open Access Journals (Sweden)

    Zehui Kong

    Full Text Available To further improve the fuel economy of series hybrid electric tracked vehicles, a reinforcement learning (RL-based real-time energy management strategy is developed in this paper. In order to utilize the statistical characteristics of online driving schedule effectively, a recursive algorithm for the transition probability matrix (TPM of power-request is derived. The reinforcement learning (RL is applied to calculate and update the control policy at regular time, adapting to the varying driving conditions. A facing-forward powertrain model is built in detail, including the engine-generator model, battery model and vehicle dynamical model. The robustness and adaptability of real-time energy management strategy are validated through the comparison with the stationary control strategy based on initial transition probability matrix (TPM generated from a long naturalistic driving cycle in the simulation. Results indicate that proposed method has better fuel economy than stationary one and is more effective in real-time control.

  20. Implementation of real-time energy management strategy based on reinforcement learning for hybrid electric vehicles and simulation validation.

    Science.gov (United States)

    Kong, Zehui; Zou, Yuan; Liu, Teng

    2017-01-01

    To further improve the fuel economy of series hybrid electric tracked vehicles, a reinforcement learning (RL)-based real-time energy management strategy is developed in this paper. In order to utilize the statistical characteristics of online driving schedule effectively, a recursive algorithm for the transition probability matrix (TPM) of power-request is derived. The reinforcement learning (RL) is applied to calculate and update the control policy at regular time, adapting to the varying driving conditions. A facing-forward powertrain model is built in detail, including the engine-generator model, battery model and vehicle dynamical model. The robustness and adaptability of real-time energy management strategy are validated through the comparison with the stationary control strategy based on initial transition probability matrix (TPM) generated from a long naturalistic driving cycle in the simulation. Results indicate that proposed method has better fuel economy than stationary one and is more effective in real-time control.

  1. Reinforcement learning design-based adaptive tracking control with less learning parameters for nonlinear discrete-time MIMO systems.

    Science.gov (United States)

    Liu, Yan-Jun; Tang, Li; Tong, Shaocheng; Chen, C L Philip; Li, Dong-Juan

    2015-01-01

    Based on the neural network (NN) approximator, an online reinforcement learning algorithm is proposed for a class of affine multiple input and multiple output (MIMO) nonlinear discrete-time systems with unknown functions and disturbances. In the design procedure, two networks are provided where one is an action network to generate an optimal control signal and the other is a critic network to approximate the cost function. An optimal control signal and adaptation laws can be generated based on two NNs. In the previous approaches, the weights of critic and action networks are updated based on the gradient descent rule and the estimations of optimal weight vectors are directly adjusted in the design. Consequently, compared with the existing results, the main contributions of this paper are: 1) only two parameters are needed to be adjusted, and thus the number of the adaptation laws is smaller than the previous results and 2) the updating parameters do not depend on the number of the subsystems for MIMO systems and the tuning rules are replaced by adjusting the norms on optimal weight vectors in both action and critic networks. It is proven that the tracking errors, the adaptation laws, and the control inputs are uniformly bounded using Lyapunov analysis method. The simulation examples are employed to illustrate the effectiveness of the proposed algorithm.

  2. Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning.

    Science.gov (United States)

    Yang, Xiong; Liu, Derong; Wang, Ding; Wei, Qinglai

    2014-07-01

    In this paper, a reinforcement-learning-based direct adaptive control is developed to deliver a desired tracking performance for a class of discrete-time (DT) nonlinear systems with unknown bounded disturbances. We investigate multi-input-multi-output unknown nonaffine nonlinear DT systems and employ two neural networks (NNs). By using Implicit Function Theorem, an action NN is used to generate the control signal and it is also designed to cancel the nonlinearity of unknown DT systems, for purpose of utilizing feedback linearization methods. On the other hand, a critic NN is applied to estimate the cost function, which satisfies the recursive equations derived from heuristic dynamic programming. The weights of both the action NN and the critic NN are directly updated online instead of offline training. By utilizing Lyapunov's direct method, the closed-loop tracking errors and the NN estimated weights are demonstrated to be uniformly ultimately bounded. Two numerical examples are provided to show the effectiveness of the present approach. Copyright © 2014 Elsevier Ltd. All rights reserved.

  3. Fun While Learning and Earning. A Look Into Chattanooga Public Schools' Token Reinforcement Program.

    Science.gov (United States)

    Smith, William F.; Sanders, Frank J.

    A token reinforcement program was used by the Piney Woods Research and Demonstration Center in Chattanooga, Tennessee. Children who were from economically deprived homes received tokens for positive behavior. The tokens were redeemable for recess privileges, ice cream, candy, and other such reinforcers. All tokens were spent on the day earned so…

  4. Developing Multi-Agency Leadership in Education

    Science.gov (United States)

    Close, Paul

    2012-01-01

    This article contributes to the growing debate around how we understand and develop multi-agency leadership in children and young people's services. Bringing together a range of inter-disciplinary research, it presents a framework for multi-agency leadership development, which, it argues, is well theorised, multi-level and versed in key field…

  5. Fairness in multi-agent systems

    NARCIS (Netherlands)

    Jong, de S.; Tuyls, K.P.; Verbeeck, K.

    2008-01-01

    Multi-agent systems are complex systems in which multiple autonomous entities, called agents, cooperate in order to achieve a common or personal goal. These entities may be computer software, robots, and also humans. In fact, many multi-agent systems are intended to operate in cooperation with or as

  6. Data Mining Process Optimization in Computational Multi-agent Systems

    OpenAIRE

    Kazík, O.; Neruda, R. (Roman)

    2015-01-01

    In this paper, we present an agent-based solution of metalearning problem which focuses on optimization of data mining processes. We exploit the framework of computational multi-agent systems in which various meta-learning problems have been already studied, e.g. parameter-space search or simple method recommendation. In this paper, we examine the effect of data preprocessing for machine learning problems. We perform the set of experiments in the search-space of data mining processes which is...

  7. Continuous theta-burst stimulation (cTBS) over the lateral prefrontal cortex alters reinforcement learning bias.

    Science.gov (United States)

    Ott, Derek V M; Ullsperger, Markus; Jocham, Gerhard; Neumann, Jane; Klein, Tilmann A

    2011-07-15

    The prefrontal cortex is known to play a key role in higher-order cognitive functions. Recently, we showed that this brain region is active in reinforcement learning, during which subjects constantly have to integrate trial outcomes in order to optimize performance. To further elucidate the role of the dorsolateral prefrontal cortex (DLPFC) in reinforcement learning, we applied continuous theta-burst stimulation (cTBS) either to the left or right DLPFC, or to the vertex as a control region, respectively, prior to the performance of a probabilistic learning task in an fMRI environment. While there was no influence of cTBS on learning performance per se, we observed a stimulation-dependent modulation of reward vs. punishment sensitivity: Left-hemispherical DLPFC stimulation led to a more reward-guided performance, while right-hemispherical cTBS induced a more avoidance-guided behavior. FMRI results showed enhanced prediction error coding in the ventral striatum in subjects stimulated over the left as compared to the right DLPFC. Both behavioral and imaging results are in line with recent findings that left, but not right-hemispherical stimulation can trigger a release of dopamine in the ventral striatum, which has been suggested to increase the relative impact of rewards rather than punishment on behavior. Copyright © 2011 Elsevier Inc. All rights reserved.

  8. Learning Sequences of Actions in Collectives of Autonomous Agents

    Science.gov (United States)

    Turner, Kagan; Agogino, Adrian K.; Wolpert, David H.; Clancy, Daniel (Technical Monitor)

    2001-01-01

    In this paper we focus on the problem of designing a collective of autonomous agents that individually learn sequences of actions such that the resultant sequence of joint actions achieves a predetermined global objective. We are particularly interested in instances of this problem where centralized control is either impossible or impractical. For single agent systems in similar domains, machine learning methods (e.g., reinforcement learners) have been successfully used. However, applying such solutions directly to multi-agent systems often proves problematic, as agents may work at cross-purposes, or have difficulty in evaluating their contribution to achievement of the global objective, or both. Accordingly, the crucial design step in multiagent systems centers on determining the private objectives of each agent so that as the agents strive for those objectives, the system reaches a good global solution. In this work we consider a version of this problem involving multiple autonomous agents in a grid world. We use concepts from collective intelligence to design goals for the agents that are 'aligned' with the global goal, and are 'learnable' in that agents can readily see how their behavior affects their utility. We show that reinforcement learning agents using those goals outperform both 'natural' extensions of single agent algorithms and global reinforcement, learning solutions based on 'team games'.

  9. Scheduled power tracking control of the wind-storage hybrid system based on the reinforcement learning theory

    Science.gov (United States)

    Li, Ze

    2017-09-01

    In allusion to the intermittency and uncertainty of the wind electricity, energy storage and wind generator are combined into a hybrid system to improve the controllability of the output power. A scheduled power tracking control method is proposed based on the reinforcement learning theory and Q-learning algorithm. In this method, the state space of the environment is formed with two key factors, i.e. the state of charge of the energy storage and the difference value between the actual wind power and scheduled power, the feasible action is the output power of the energy storage, and the corresponding immediate rewarding function is designed to reflect the rationality of the control action. By interacting with the environment and learning from the immediate reward, the optimal control strategy is gradually formed. After that, it could be applied to the scheduled power tracking control of the hybrid system. Finally, the rationality and validity of the method are verified through simulation examples.

  10. Oxytocin attenuates trust as a subset of more general reinforcement learning, with altered reward circuit functional connectivity in males.

    Science.gov (United States)

    Ide, Jaime S; Nedic, Sanja; Wong, Kin F; Strey, Shmuel L; Lawson, Elizabeth A; Dickerson, Bradford C; Wald, Lawrence L; La Camera, Giancarlo; Mujica-Parodi, Lilianne R

    2018-07-01

    Oxytocin (OT) is an endogenous neuropeptide that, while originally thought to promote trust, has more recently been found to be context-dependent. Here we extend experimental paradigms previously restricted to de novo decision-to-trust, to a more realistic environment in which social relationships evolve in response to iterative feedback over twenty interactions. In a randomized, double blind, placebo-controlled within-subject/crossover experiment of human adult males, we investigated the effects of a single dose of intranasal OT (40 IU) on Bayesian expectation updating and reinforcement learning within a social context, with associated brain circuit dynamics. Subjects participated in a neuroeconomic task (Iterative Trust Game) designed to probe iterative social learning while their brains were scanned using ultra-high field (7T) fMRI. We modeled each subject's behavior using Bayesian updating of belief-states ("willingness to trust") as well as canonical measures of reinforcement learning (learning rate, inverse temperature). Behavioral trajectories were then used as regressors within fMRI activation and connectivity analyses to identify corresponding brain network functionality affected by OT. Behaviorally, OT reduced feedback learning, without bias with respect to positive versus negative reward. Neurobiologically, reduced learning under OT was associated with muted communication between three key nodes within the reward circuit: the orbitofrontal cortex, amygdala, and lateral (limbic) habenula. Our data suggest that OT, rather than inspiring feelings of generosity, instead attenuates the brain's encoding of prediction error and therefore its ability to modulate pre-existing beliefs. This effect may underlie OT's putative role in promoting what has typically been reported as 'unjustified trust' in the face of information that suggests likely betrayal, while also resolving apparent contradictions with regard to OT's context-dependent behavioral effects. Copyright

  11. From Creatures of Habit to Goal-Directed Learners: Tracking the Developmental Emergence of Model-Based Reinforcement Learning.

    Science.gov (United States)

    Decker, Johannes H; Otto, A Ross; Daw, Nathaniel D; Hartley, Catherine A

    2016-06-01

    Theoretical models distinguish two decision-making strategies that have been formalized in reinforcement-learning theory. A model-based strategy leverages a cognitive model of potential actions and their consequences to make goal-directed choices, whereas a model-free strategy evaluates actions based solely on their reward history. Research in adults has begun to elucidate the psychological mechanisms and neural substrates underlying these learning processes and factors that influence their relative recruitment. However, the developmental trajectory of these evaluative strategies has not been well characterized. In this study, children, adolescents, and adults performed a sequential reinforcement-learning task that enabled estimation of model-based and model-free contributions to choice. Whereas a model-free strategy was apparent in choice behavior across all age groups, a model-based strategy was absent in children, became evident in adolescents, and strengthened in adults. These results suggest that recruitment of model-based valuation systems represents a critical cognitive component underlying the gradual maturation of goal-directed behavior. © The Author(s) 2016.

  12. 2015 Special Sessions of the 13th International Conference on Practical Applications of Agents and Multi-Agent Systems

    CERN Document Server

    Hernández, Josefa; Mathieu, Philippe; Campbell, Andrew; Fernández-Caballero, Antonio; Moreno, María; Julián, Vicente; Alonso-Betanzos, Amparo; Jiménez-López, María; Botti, Vicente; Trends in Practical Applications of Agents, Multi-Agent Systems and Sustainability : the PAAMS Collection

    2015-01-01

    This volume presents the papers that have been accepted for the 2015 special sessions of the 13th International Conference on Practical Applications of Agents and Multi-Agent Systems, held at University of Salamanca, Spain, at 3rd-5th June, 2015: Agents Behaviours and Artificial Markets (ABAM); Agents and Mobile Devices (AM); Multi-Agent Systems and Ambient Intelligence (MASMAI); Web Mining and Recommender systems (WebMiRes); Learning, Agents and Formal Languages (LAFLang); Agent-based Modeling of Sustainable Behavior and Green Economies (AMSBGE); Emotional Software Agents (SSESA) and Intelligent Educational Systems (SSIES). The volume also includes the paper accepted for the Doctoral Consortium in PAAMS 2015. PAAMS, the International Conference on Practical Applications of Agents and Multi-Agent Systems is an evolution of the International Workshop on Practical Applications of Agents and Multi-Agent Systems. PAAMS is an international yearly tribune to present, to discuss, and to disseminate the latest develo...

  13. Multi-agent and complex systems

    CERN Document Server

    Ren, Fenghui; Fujita, Katsuhide; Zhang, Minjie; Ito, Takayuki

    2017-01-01

    This book provides a description of advanced multi-agent and artificial intelligence technologies for the modeling and simulation of complex systems, as well as an overview of the latest scientific efforts in this field. A complex system features a large number of interacting components, whose aggregate activities are nonlinear and self-organized. A multi-agent system is a group or society of agents which interact with others cooperatively and/or competitively in order to reach their individual or common goals. Multi-agent systems are suitable for modeling and simulation of complex systems, which is difficult to accomplish using traditional computational approaches.

  14. An Interactive Tool for Creating Multi-Agent Systems and Interactive Agent-based Games

    DEFF Research Database (Denmark)

    Lund, Henrik Hautop; Pagliarini, Luigi

    2011-01-01

    Utilizing principles from parallel and distributed processing combined with inspiration from modular robotics, we developed the modular interactive tiles. As an educational tool, the modular interactive tiles facilitate the learning of multi-agent systems and interactive agent-based games...

  15. Metamodeling of Semantic Web Enabled Multiagent Systems

    NARCIS (Netherlands)

    Kardas, G.; Göknil, Arda; Dikenelli, O.; Topaloglu, N.Y.; Weyns, D.; Holvoet, T.

    2006-01-01

    Several agent researchers are currently studying agent modeling and they propose dierent architectural metamodels for developing Multiagent Systems (MAS) according to specic agent development methodologies. When support for Semantic Web technology and its related constructs are considered, agent

  16. Argumentation and Multi-Agent Decision Making

    OpenAIRE

    Parsons, S.; Jennings, N. R.

    1998-01-01

    This paper summarises our on-going work on mixed- initiative decision making which extends both classical decision theory and a symbolic theory of decision making based on argumentation to a multi-agent domain.

  17. The Uses and Limits of Social Reinforcement and Industriousness for Learning to Read. Technical Report #60.

    Science.gov (United States)

    Tharp, Roland G.; Gallimore, Ronald

    This report describes a study of the use of social reinforcement to increase the industriousness, and subsequently the reading competence, of children in the kindergarten through third grade classes of the Kamehameha Early Education Program (KEEP) demonstration school. Teacher behaviors, pupil industriousness, and pupil reading performance were…

  18. Multiagent Work Practice Simulation: Progress and Challenges

    Science.gov (United States)

    Clancey, William J.; Sierhuis, Maarten

    2002-01-01

    Modeling and simulating complex human-system interactions requires going beyond formal procedures and information flows to analyze how people interact with each other. Such work practices include conversations, modes of communication, informal assistance, impromptu meetings, workarounds, and so on. To make these social processes visible, we have developed a multiagent simulation tool, called Brahms, for modeling the activities of people belonging to multiple groups, situated in a physical environment (geographic regions, buildings, transport vehicles, etc.) consisting of tools, documents, and computer systems. We are finding many useful applications of Brahms for system requirements analysis, instruction, implementing software agents, and as a workbench for relating cognitive and social theories of human behavior. Many challenges remain for representing work practices, including modeling: memory over multiple days, scheduled activities combining physical objects, groups, and locations on a timeline (such as a Space Shuttle mission), habitat vehicles with trajectories (such as the Shuttle), agent movement in 3d space (e.g., inside the International Space Station), agent posture and line of sight, coupled movements (such as carrying objects), and learning (mimicry, forming habits, detecting repetition, etc.).

  19. BRAIN Journal - Cognitive Medical Multiagent Systems

    OpenAIRE

    Barna Iantovics

    2017-01-01

    Abstract The development of efficient and flexible agent-based medical diagnosis systems represents a recent research direction. Medical multiagent systems may improve the efficiency of traditionally developed medical computational systems, like the medical expert systems. In our previous researches, a novel cooperative medical diagnosis multiagent system called CMDS (Contract Net Based Medical Diagnosis System) was proposed. CMDS system can solve flexibly a large variety of medical diagn...

  20. Multiagent voltage and reactive power control system

    Directory of Open Access Journals (Sweden)

    I. Arkhipov

    2014-12-01

    Full Text Available This paper is devoted to the research of multiagent voltage and reactive power control system development. The prototype of the system has been developed by R&D Center at FGC UES (Russia. The control system architecture is based on the innovative multiagent system theory application that leads to the achievement of several significant advantages (in comparison to traditional control systems implementation such as control system efficiency enhancement, control system survivability and cyber security.

  1. Lack of effect of Pitressin on the learning ability of Brattleboro rats with diabetes insipidus using positively reinforced operant conditioning.

    Science.gov (United States)

    Laycock, J F; Gartside, I B

    1985-08-01

    Brattleboro rats with hereditary hypothalamic diabetes insipidus (BDI) received daily subcutaneous injections of vasopressin in the form of Pitressin tannate (0.5 IU/24 hr). They were initially deprived of food and then trained to work for food reward in a Skinner box to a fixed ratio of ten presses for each pellet received. Once this schedule had been learned the rats were given a discrimination task daily for seven days. The performances of these BDI rats were compared with those of rats of the parent Long Evans (LE) strain receiving daily subcutaneous injections of vehicle (arachis oil). Comparisons were also made between these two groups of treated animals and untreated BDI and LE rats studied under similar conditions. In the initial learning trial, both control and Pitressin-treated BDI rats performed significantly better, and manifested less fear initially, than the control or vehicle-injected LE rats when first placed in the Skinner box. Once the initial task had been learned there was no marked difference in the discrimination learning between control or treated BDI and LE animals. These results support the view that vasopressin is not directly involved in all types of learning behaviour, particularly those involving positively reinforced operant conditioning.

  2. Dopaminergic control of motivation and reinforcement learning: a closed-circuit account for reward-oriented behavior.

    Science.gov (United States)

    Morita, Kenji; Morishima, Mieko; Sakai, Katsuyuki; Kawaguchi, Yasuo

    2013-05-15

    Humans and animals take actions quickly when they expect that the actions lead to reward, reflecting their motivation. Injection of dopamine receptor antagonists into the striatum has been shown to slow such reward-seeking behavior, suggesting that dopamine is involved in the control of motivational processes. Meanwhile, neurophysiological studies have revealed that phasic response of dopamine neurons appears to represent reward prediction error, indicating that dopamine plays central roles in reinforcement learning. However, previous attempts to elucidate the mechanisms of these dopaminergic controls have not fully explained how the motivational and learning aspects are related and whether they can be understood by the way the activity of dopamine neurons itself is controlled by their upstream circuitries. To address this issue, we constructed a closed-circuit model of the corticobasal ganglia system based on recent findings regarding intracortical and corticostriatal circuit architectures. Simulations show that the model could reproduce the observed distinct motivational effects of D1- and D2-type dopamine receptor antagonists. Simultaneously, our model successfully explains the dopaminergic representation of reward prediction error as observed in behaving animals during learning tasks and could also explain distinct choice biases induced by optogenetic stimulation of the D1 and D2 receptor-expressing striatal neurons. These results indicate that the suggested roles of dopamine in motivational control and reinforcement learning can be understood in a unified manner through a notion that the indirect pathway of the basal ganglia represents the value of states/actions at a previous time point, an empirically driven key assumption of our model.

  3. Multi-Agent Software Engineering

    International Nuclear Information System (INIS)

    Mohamed, A.H.

    2014-01-01

    This paper proposed an alarm-monitoring system for people based on multi-agent using maps. The system monitors the users physical context using their mobile phone. The agents on the mobile phones are responsible for collecting, processing and sending data to the server. They can determine the parameters of their environment by sensors. The data are processed and sent to the server. On the other side, a set of agents on server can store this data and check the preconditions of the restrictions associated with the user, in order to trigger the appropriate alarms. These alarms are sent not only to the user who is alarmed to avoid the appeared restriction, but also to his supervisor. The proposed system is a general purpose alarm system that can be used in different critical application areas. It has been applied for monitoring the workers of radiation sites. However, these workers can do their activity tasks in the radiation environments safely

  4. Feedback for reinforcement learning based brain-machine interfaces using confidence metrics

    Science.gov (United States)

    Prins, Noeline W.; Sanchez, Justin C.; Prasad, Abhishek

    2017-06-01

    Objective. For brain-machine interfaces (BMI) to be used in activities of daily living by paralyzed individuals, the BMI should be as autonomous as possible. One of the challenges is how the feedback is extracted and utilized in the BMI. Our long-term goal is to create autonomous BMIs that can utilize an evaluative feedback from the brain to update the decoding algorithm and use it intelligently in order to adapt the decoder. In this study, we show how to extract the necessary evaluative feedback from a biologically realistic (synthetic) source, use both the quantity and the quality of the feedback, and how that feedback information can be incorporated into a reinforcement learning (RL) controller architecture to maximize its performance. Approach. Motivated by the perception-action-reward cycle (PARC) in the brain which links reward for cognitive decision making and goal-directed behavior, we used a reward-based RL architecture named Actor-Critic RL as the model. Instead of using an error signal towards building an autonomous BMI, we envision to use a reward signal from the nucleus accumbens (NAcc) which plays a key role in the linking of reward to motor behaviors. To deal with the complexity and non-stationarity of biological reward signals, we used a confidence metric which was used to indicate the degree of feedback accuracy. This confidence was added to the Actor’s weight update equation in the RL controller architecture. If the confidence was high (>0.2), the BMI decoder used this feedback to update its parameters. However, when the confidence was low, the BMI decoder ignored the feedback and did not update its parameters. The range between high confidence and low confidence was termed as the ‘ambiguous’ region. When the feedback was within this region, the BMI decoder updated its weight at a lower rate than when fully confident, which was decided by the confidence. We used two biologically realistic models to generate synthetic data for MI (Izhikevich

  5. Environmental Impact: Reinforce a Culture of Continuous Learning with These Key Elements

    Science.gov (United States)

    Edwards, Brian; Gammell, Jessica

    2017-01-01

    Fostering a robust professional learning culture in schools is vital for attracting and retaining high-caliber talent. Education leaders are looking for guidance on how to establish and sustain an environment that fosters continuous learning. Based on their experience in helping educators design and implement professional learning systems, the…

  6. Reaching control of a full-torso, modelled musculoskeletal robot using muscle synergies emergent under reinforcement learning

    International Nuclear Information System (INIS)

    Diamond, A; Holland, O E

    2014-01-01

    ‘Anthropomimetic’ robots mimic both human morphology and internal structure—skeleton, muscles, compliance and high redundancy—thus presenting a formidable challenge to conventional control. Here we derive a novel controller for this class of robot which learns effective reaching actions through the sustained activation of weighted muscle synergies, an approach which draws upon compelling, recent evidence from animal and human studies, but is almost unexplored to date in the musculoskeletal robot literature. Since the effective synergy patterns for a given robot will be unknown, we derive a reinforcement-learning approach intended to allow their emergence, in particular those patterns aiding linearization of control. Using an extensive physics-based model of the anthropomimetic ECCERobot, we find that effective reaching actions can be learned comprising only two sequential motor co-activation patterns, each controlled by just a single common driving signal. Factor analysis shows the emergent muscle co-activations can be largely reconstructed using weighted combinations of only 13 common fragments. Testing these ‘candidate’ synergies as drivable units, the same controller now learns the reaching task both faster and better. (paper)

  7. Rats bred for helplessness exhibit positive reinforcement learning deficits which are not alleviated by an antidepressant dose of the MAO-B inhibitor deprenyl.

    Science.gov (United States)

    Schulz, Daniela; Henn, Fritz A; Petri, David; Huston, Joseph P

    2016-08-04

    Principles of negative reinforcement learning may play a critical role in the etiology and treatment of depression. We examined the integrity of positive reinforcement learning in congenitally helpless (cH) rats, an animal model of depression, using a random ratio schedule and a devaluation-extinction procedure. Furthermore, we tested whether an antidepressant dose of the monoamine oxidase (MAO)-B inhibitor deprenyl would reverse any deficits in positive reinforcement learning. We found that cH rats (n=9) were impaired in the acquisition of even simple operant contingencies, such as a fixed interval (FI) 20 schedule. cH rats exhibited no apparent deficits in appetite or reward sensitivity. They reacted to the devaluation of food in a manner consistent with a dose-response relationship. Reinforcer motivation as assessed by lever pressing across sessions with progressively decreasing reward probabilities was highest in congenitally non-helpless (cNH, n=10) rats as long as the reward probabilities remained relatively high. cNH compared to wild-type (n=10) rats were also more resistant to extinction across sessions. Compared to saline (n=5), deprenyl (n=5) reduced the duration of immobility of cH rats in the forced swimming test, indicative of antidepressant effects, but did not restore any deficits in the acquisition of a FI 20 schedule. We conclude that positive reinforcement learning was impaired in rats bred for helplessness, possibly due to motivational impairments but not deficits in reward sensitivity, and that deprenyl exerted antidepressant effects but did not reverse the deficits in positive reinforcement learning. Copyright © 2016 IBRO. Published by Elsevier Ltd. All rights reserved.

  8. Impulsive Flocking of Dynamical Multiagent Systems with External Disturbances

    Directory of Open Access Journals (Sweden)

    Fujun Han

    2017-01-01

    Full Text Available Flocking motion of multiagent systems is influenced by various external disturbances in complex environment. By applying disturbance observer, flocking of multiagent systems with exogenous disturbances is studied. Based on the robust features of impulsive control, a distributed impulsive control protocol is presented with disturbance observer, and flocking motion of multiagent systems is analyzed. Moreover, a sufficient condition is obtained to ensure the flocking motion of multiagent systems following a leader. Finally, simulation results show the validity of the theoretical conclusion.

  9. Insights in reinforcement rearning : formal analysis and empirical evaluation of temporal-difference learning algorithms

    NARCIS (Netherlands)

    van Hasselt, H.P.

    2011-01-01

    A key aspect of artificial intelligence is the ability to learn from experience. If examples of correct solutions exist, supervised learning techniques can be used to predict what the correct solution will be for future observations. However, often such examples are not readily available. The field

  10. Reinforcing Comprehensive Business Learning through an Undergraduate Retailing Course: A Prospectus

    Science.gov (United States)

    Ahmed, Irfan

    2009-01-01

    Undergraduate programs in business are expected to provide a comprehensive learning for their students in order to prepare them to be able to deal with complex business problems in their jobs. Business schools attempt to provide this learning through various curricular design strategies. This paper proposes the use of an undergraduate course in…

  11. Empirical Evidence of Priming, Transfer, Reinforcement, and Learning in the Real and Virtual Trillium Trails

    Science.gov (United States)

    Harrington, M. C. R.

    2011-01-01

    Over the past 20 years, there has been a debate on the effectiveness of virtual reality used for learning with young children, producing many ideas but little empirical proof. This empirical study compared learning activity in situ of a real environment (Real) and a desktop virtual reality (Virtual) environment, built with video game technology,…

  12. Real time reinforcement learning control of dynamic systems applied to an inverted pendulum

    NARCIS (Netherlands)

    van Luenen, W.T.C.; van Luenen, W.T.C.; Stender, J.; Addis, T.

    1990-01-01

    Describes work started in order to investigate the use of neural networks for application in adaptive or learning control systems. Neural networks have learning capabilities and they can be used to realize non-linear mappings. These are attractive features which could make them useful building

  13. Continuous-time on-policy neural reinforcement learning of working memory tasks

    NARCIS (Netherlands)

    D. Zambrano (Davide); P.R. Roelfsema; S.M. Bohte (Sander)

    2015-01-01

    htmlabstractAs living organisms, one of our primary characteristics is the ability to rapidly process and react to unknown and unexpected events. To this end, we are able to recognize an event or a sequence of events and learn to respond properly. Despite advances in machine learning, current

  14. Metacognitive Monkeys or Associative Animals? Simple Reinforcement Learning Explains Uncertainty in Nonhuman Animals

    Science.gov (United States)

    Le Pelley, M. E.

    2012-01-01

    Monkeys will selectively and adaptively learn to avoid the most difficult trials of a perceptual discrimination learning task. Couchman, Coutinho, Beran, and Smith (2010) have recently demonstrated that this pattern of responding does not depend on animals receiving trial-by-trial feedback for their responses; it also obtains if experience of the…

  15. Application Of Reinforcement Learning In Heading Control Of A Fixed Wing UAV Using X-Plane Platform

    Directory of Open Access Journals (Sweden)

    Kimathi

    2017-02-01

    Full Text Available Heading control of an Unmanned Aerial Vehicle UAV is a vital operation of an autopilot system. It is executed by employing a design of control algorithms that control its direction and navigation. Most commonly available autopilots exploit Proportional-Integral-Derivative PID based heading controllers. In this paper we propose an online adaptive reinforcement learning heading controller. The autopilot heading controller will be designed in MatlabSimulink for controlling a UAV in X-Plane test platform. Through this platform the performance of the controller is shown using real time simulations. The performance of this controller is compared to that of a PID controller. The results show that the proposed method performs better than a well tuned PID controller.

  16. An Energy-Efficient Spectrum-Aware Reinforcement Learning-Based Clustering Algorithm for Cognitive Radio Sensor Networks.

    Science.gov (United States)

    Mustapha, Ibrahim; Mohd Ali, Borhanuddin; Rasid, Mohd Fadlee A; Sali, Aduwati; Mohamad, Hafizal

    2015-08-13

    It is well-known that clustering partitions network into logical groups of nodes in order to achieve energy efficiency and to enhance dynamic channel access in cognitive radio through cooperative sensing. While the topic of energy efficiency has been well investigated in conventional wireless sensor networks, the latter has not been extensively explored. In this paper, we propose a reinforcement learning-based spectrum-aware clustering algorithm that allows a member node to learn the energy and cooperative sensing costs for neighboring clusters to achieve an optimal solution. Each member node selects an optimal cluster that satisfies pairwise constraints, minimizes network energy consumption and enhances channel sensing performance through an exploration technique. We first model the network energy consumption and then determine the optimal number of clusters for the network. The problem of selecting an optimal cluster is formulated as a Markov Decision Process (MDP) in the algorithm and the obtained simulation results show convergence, learning and adaptability of the algorithm to dynamic environment towards achieving an optimal solution. Performance comparisons of our algorithm with the Groupwise Spectrum Aware (GWSA)-based algorithm in terms of Sum of Square Error (SSE), complexity, network energy consumption and probability of detection indicate improved performance from the proposed approach. The results further reveal that an energy savings of 9% and a significant Primary User (PU) detection improvement can be achieved with the proposed approach.

  17. RLAM: A Dynamic and Efficient Reinforcement Learning-Based Adaptive Mapping Scheme in Mobile WiMAX Networks

    Directory of Open Access Journals (Sweden)

    M. Louta

    2014-01-01

    Full Text Available WiMAX (Worldwide Interoperability for Microwave Access constitutes a candidate networking technology towards the 4G vision realization. By adopting the Orthogonal Frequency Division Multiple Access (OFDMA technique, the latest IEEE 802.16x amendments manage to provide QoS-aware access services with full mobility support. A number of interesting scheduling and mapping schemes have been proposed in research literature. However, they neglect a considerable asset of the OFDMA-based wireless systems: the dynamic adjustment of the downlink-to-uplink width ratio. In order to fully exploit the supported mobile WiMAX features, we design, develop, and evaluate a rigorous adaptive model, which inherits its main aspects from the reinforcement learning field. The model proposed endeavours to efficiently determine the downlink-to-uplinkwidth ratio, on a frame-by-frame basis, taking into account both the downlink and uplink traffic in the Base Station (BS. Extensive evaluation results indicate that the model proposed succeeds in providing quite accurate estimations, keeping the average error rate below 15% with respect to the optimal sub-frame configurations. Additionally, it presents improved performance compared to other learning methods (e.g., learning automata and notable improvements compared to static schemes that maintain a fixed predefined ratio in terms of service ratio and resource utilization.

  18. A new computational account of cognitive control over reinforcement-based decision-making: Modeling of a probabilistic learning task.

    Science.gov (United States)

    Zendehrouh, Sareh

    2015-11-01

    Recent work on decision-making field offers an account of dual-system theory for decision-making process. This theory holds that this process is conducted by two main controllers: a goal-directed system and a habitual system. In the reinforcement learning (RL) domain, the habitual behaviors are connected with model-free methods, in which appropriate actions are learned through trial-and-error experiences. However, goal-directed behaviors are associated with model-based methods of RL, in which actions are selected using a model of the environment. Studies on cognitive control also suggest that during processes like decision-making, some cortical and subcortical structures work in concert to monitor the consequences of decisions and to adjust control according to current task demands. Here a computational model is presented based on dual system theory and cognitive control perspective of decision-making. The proposed model is used to simulate human performance on a variant of probabilistic learning task. The basic proposal is that the brain implements a dual controller, while an accompanying monitoring system detects some kinds of conflict including a hypothetical cost-conflict one. The simulation results address existing theories about two event-related potentials, namely error related negativity (ERN) and feedback related negativity (FRN), and explore the best account of them. Based on the results, some testable predictions are also presented. Copyright © 2015 Elsevier Ltd. All rights reserved.

  19. Computational Properties of the Hippocampus Increase the Efficiency of Goal-Directed Foraging through Hierarchical Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Eric Chalmers

    2016-12-01

    Full Text Available The mammalian brain is thought to use a version of Model-based Reinforcement Learning (MBRL to guide goal-directed behavior, wherein animals consider goals and make plans to acquire desired outcomes. However, conventional MBRL algorithms do not fully explain animals’ ability to rapidly adapt to environmental changes, or learn multiple complex tasks. They also require extensive computation, suggesting that goal-directed behavior is cognitively expensive. We propose here that key features of processing in the hippocampus support a flexible MBRL mechanism for spatial navigation that is computationally efficient and can adapt quickly to change. We investigate this idea by implementing a computational MBRL framework that incorporates features inspired by computational properties of the hippocampus: a hierarchical representation of space, forward sweeps through future spatial trajectories, and context-driven remapping of place cells. We find that a hierarchical abstraction of space greatly reduces the computational load (mental effort required for adaptation to changing environmental conditions, and allows efficient scaling to large problems. It also allows abstract knowledge gained at high levels to guide adaptation to new obstacles. Moreover, a context-driven remapping mechanism allows learning and memory of multiple tasks. Simulating dorsal or ventral hippocampal lesions in our computational framework qualitatively reproduces behavioral deficits observed in rodents with analogous lesions. The framework may thus embody key features of how the brain organizes model-based RL to efficiently solve navigation and other difficult tasks.

  20. Assist-as-needed robotic trainer based on reinforcement learning and its application to dart-throwing.

    Science.gov (United States)

    Obayashi, Chihiro; Tamei, Tomoya; Shibata, Tomohiro

    2014-05-01

    This paper proposes a novel robotic trainer for motor skill learning. It is user-adaptive inspired by the assist-as-needed principle well known in the field of physical therapy. Most previous studies in the field of the robotic assistance of motor skill learning have used predetermined desired trajectories, and it has not been examined intensively whether these trajectories were optimal for each user. Furthermore, the guidance hypothesis states that humans tend to rely too much on external assistive feedback, resulting in interference with the internal feedback necessary for motor skill learning. A few studies have proposed a system that adjusts its assistive strength according to the user's performance in order to prevent the user from relying too much on the robotic assistance. There are, however, problems in these studies, in that a physical model of the user's motor system is required, which is inherently difficult to construct. In this paper, we propose a framework for a robotic trainer that is user-adaptive and that neither requires a specific desired trajectory nor a physical model of the user's motor system, and we achieve this using model-free reinforcement learning. We chose dart-throwing as an example motor-learning task as it is one of the simplest throwing tasks, and its performance can easily be and quantitatively measured. Training experiments with novices, aiming at maximizing the score with the darts and minimizing the physical robotic assistance, demonstrate the feasibility and plausibility of the proposed framework. Copyright © 2014 Elsevier Ltd. All rights reserved.

  1. Layered Learning in Multi-Agent Systems

    Science.gov (United States)

    1998-12-15

    project almost from the beginning has tirelessly experimented with different robot architectures, always managing to pull things together and create...TEAM MEMBER AGENT ARCHITECTURE I " ! Midfielder, Left : • i ) ( ^ J Goalie , Center Home Coordinates Home Range Max Range Figure

  2. Building Multi-Agent Systems Using Jason

    DEFF Research Database (Denmark)

    Boss, Niklas Skamriis; Jensen, Andreas Schmidt; Villadsen, Jørgen

    2010-01-01

    We provide a detailed description of the Jason-DTU system, including the used methodology, tools as well as team strategy. We also discuss the experience gathered in the contest. In spring 2009 the course “Artificial Intelligence and Multi- Agent Systems” was held for the first time...... on the Technical University of Denmark (DTU). A part of this course was a short introduction to the multi-agent framework Jason, which is an interpreter for AgentSpeak, an agent-oriented programming language. As the final project in this course a solution to the Multi-Agent Programming Contest from 2007, the Gold...

  3. Improving Multi-Agent Systems Using Jason

    DEFF Research Database (Denmark)

    Vester, Steen; Boss, Niklas Skamriis; Jensen, Andreas Schmidt

    2011-01-01

    We describe the approach used to develop the multi-agent system of herders that competed as the Jason-DTU team at the Multi-Agent Programming Contest 2010. We also participated in 2009 with a system developed in the agentoriented programming language Jason which is an extension of AgentSpeak. We ...... used the implementation from 2009 as a foundation and therefore much of the work done this year was on improving that implementation. We present a description which includes design and analysis of the system as well as the main features of our agent team strategy. In addition we discuss...

  4. Multi-agent systems simulation and applications

    CERN Document Server

    Uhrmacher, Adelinde M

    2009-01-01

    Methodological Guidelines for Modeling and Developing MAS-Based SimulationsThe intersection of agents, modeling, simulation, and application domains has been the subject of active research for over two decades. Although agents and simulation have been used effectively in a variety of application domains, much of the supporting research remains scattered in the literature, too often leaving scientists to develop multi-agent system (MAS) models and simulations from scratch. Multi-Agent Systems: Simulation and Applications provides an overdue review of the wide ranging facets of MAS simulation, i

  5. Heads for learning, tails for memory: Reward, reinforcement and a role of dopamine in determining behavioural relevance across multiple timescales

    Directory of Open Access Journals (Sweden)

    Mathieu eBaudonnat

    2013-10-01

    Full Text Available Dopamine has long been tightly associated with aspects of reinforcement learning and motivation in simple situations where there are a limited number of stimuli to guide behaviour and constrained range of outcomes. In naturalistic situations, however, there are many potential cues and foraging strategies that could be adopted, and it is critical that animals determine what might be behaviourally relevant in such complex environments. This requires not only detecting discrepancies with what they have recently experienced, but also identifying similarities with past experiences stored in memory. Here, we review what role dopamine might play in determining how and when to learn about the world, and how to develop choice policies appropriate to the situation faced. We discuss evidence that dopamine is shaped by motivation and memory and in turn shapes reward-based memory formation. In particular, we suggest that hippocampal-striatal-dopamine networks may interact to determine how surprising the world is and to either inhibit or promote actions at time of behavioural uncertainty.

  6. Immediate and Long-Term Memory for Reinforcement Context: The Development of Learned Expectancies in Early Infancy.

    Science.gov (United States)

    Mast, Vicki K.; And Others

    1980-01-01

    Tested the persistence over 24 hours of reward-expectation habits in infants. A comparison was made between the responses of two groups of infants (infants with a history of reinforcement with large, complex mobiles, and infants with no prior history of reinforcement with mobiles) on a task reinforced by a small mobile. (Author/SS)

  7. Reinforcement Learning of Linking and Tracing Contours in Recurrent Neural Networks

    Science.gov (United States)

    Brosch, Tobias; Neumann, Heiko; Roelfsema, Pieter R.

    2015-01-01

    The processing of a visual stimulus can be subdivided into a number of stages. Upon stimulus presentation there is an early phase of feedforward processing where the visual information is propagated from lower to higher visual areas for the extraction of basic and complex stimulus features. This is followed by a later phase where horizontal connections within areas and feedback connections from higher areas back to lower areas come into play. In this later phase, image elements that are behaviorally relevant are grouped by Gestalt grouping rules and are labeled in the cortex with enhanced neuronal activity (object-based attention in psychology). Recent neurophysiological studies revealed that reward-based learning influences these recurrent grouping processes, but it is not well understood how rewards train recurrent circuits for perceptual organization. This paper examines the mechanisms for reward-based learning of new grouping rules. We derive a learning rule that can explain how rewards influence the information flow through feedforward, horizontal and feedback connections. We illustrate the efficiency with two tasks that have been used to study the neuronal correlates of perceptual organization in early visual cortex. The first task is called contour-integration and demands the integration of collinear contour elements into an elongated curve. We show how reward-based learning causes an enhancement of the representation of the to-be-grouped elements at early levels of a recurrent neural network, just as is observed in the visual cortex of monkeys. The second task is curve-tracing where the aim is to determine the endpoint of an elongated curve composed of connected image elements. If trained with the new learning rule, neural networks learn to propagate enhanced activity over the curve, in accordance with neurophysiological data. We close the paper with a number of model predictions that can be tested in future neurophysiological and computational studies

  8. An Online Social Networking Approach to Reinforce Learning of Rocks and Minerals

    Science.gov (United States)

    Kennelly, Patrick

    2009-01-01

    Numerous and varied methods are used in introductory Earth science and geology classes to help students learn about rocks and minerals, such as classroom lectures, laboratory specimen identification, and field trips. This paper reports on a method using online social networking. The choice of this forum was based on two criteria. First, many…

  9. Patterns of Learning in Verbal Discrimination as an Interaction of Social Reinforcement and Sex Combinations

    Science.gov (United States)

    Ratliff, Richard G.; And Others

    1976-01-01

    A total of 540 college students were run in two verbal discrimination learning studies (the second, a replication of the first) with one of three verbal reward conditions. In both studies, equal numbers of male and female subjects were run in each reward condition by each male and female experimenter. (MS)

  10. Roles of Approval Motivation and Generalized Expectancy for Reinforcement in Children's Conceptual Discrimination Learning

    Science.gov (United States)

    Nyce, Peggy A.; And Others

    1977-01-01

    Forty-four third graders were given a two-choice conceptual discrimination learning task. The two major factors were (1) four treatment groups varying at the extremes on two personality measures, approval motivation and locus of control and (2) sex. (MS)

  11. Road Artery Traffic Light Optimization with Use of the Reinforcement Learning

    Directory of Open Access Journals (Sweden)

    Rok Marsetič

    2014-04-01

    Full Text Available The basic principle of optimal traffic control is the appropriate real-time response to dynamic traffic flow changes. Signal plan efficiency depends on a large number of input parameters. An actuated signal system can adjust very well to traffic conditions, but cannot fully adjust to stochastic traffic volume oscillation. Due to the complexity of the problem analytical methods are not applicable for use in real time, therefore the purpose of this paper is to introduce heuristic method suitable for traffic light optimization in real time. With the evolution of artificial intelligence new possibilities for solving complex problems have been introduced. The goal of this paper is to demonstrate that the use of the Q learning algorithm for traffic lights optimization is suitable. The Q learning algorithm was verified on a road artery with three intersections. For estimation of the effectiveness and efficiency of the proposed algorithm comparison with an actuated signal plan was carried out. The results (average delay per vehicle and the number of vehicles that left road network show that Q learning algorithm outperforms the actuated signal controllers. The proposed algorithm converges to the minimal delay per vehicle regardless of the stochastic nature of traffic. In this research the impact of the model parameters (learning rate, exploration rate, influence of communication between agents and reward type on algorithm effectiveness were analysed as well.

  12. Using Social Media to Reinforce Environmental Learning and Action-Taking for School Students

    Science.gov (United States)

    Warner, Alan; Eames, Chris; Irving, Robyn

    2014-01-01

    Environmental experiences often engage learners and create an intention to act, which is then not followed through once the learner is removed from the environment. This study utilized an exploratory, interpretive framework with younger primary school classes to investigate if transfer of learning from field trip experiences "in" and…

  13. Are You Smarter Than a Teenager? Maybe Not When It Comes to Reinforcement Learning.

    Science.gov (United States)

    DiMenichi, Brynne C; Tricomi, Elizabeth

    2016-10-05

    Adolescence is a time of tumultuous behavior that may result, in part, from brain circuitry that enhances reward seeking. In this issue of Neuron, Davidow et al. (2016) present a convincing argument that adolescent brain functionality can be adaptive in certain contexts, particularly probabilistic learning environments. Copyright © 2016. Published by Elsevier Inc.

  14. Semiotics, Multi-Agent Systems and Organizations

    NARCIS (Netherlands)

    Gazendam, H.W.M.; Jorna, René J.

    1998-01-01

    Multi-agent systems are promising as models of organization because they are based on the idea that most work in human organizations is done based on intelligence, communication, cooperation, and massive parallel processing. They offer an alternative for system theories of organization, which are

  15. Adaptive hierarchical multi-agent organizations

    NARCIS (Netherlands)

    Ghijsen, M.; Jansweijer, W.N.H.; Wielinga, B.J.; Babuška, R.; Groen, F.C.A.

    2010-01-01

    In this chapter, we discuss the design of adaptive hierarchical organizations for multi-agent systems (MAS). Hierarchical organizations have a number of advantages such as their ability to handle complex problems and their scalability to large organizations. By introducing adaptivity in the

  16. Cooperative heuristic multi-agent planning

    NARCIS (Netherlands)

    De Weerdt, M.M.; Tonino, J.F.M.; Witteveen, C.

    2001-01-01

    In this paper we will use the framework to study cooperative heuristic multi-agent planning. During the construction of their plans, the agents use a heuristic function inspired by the FF planner (l3l). At any time in the process of planning the agents may exchange available resources, or they may

  17. Nash social welfare in multiagent resource allocation

    NARCIS (Netherlands)

    Ramezani, S.; Endriss, U.; David, E.; Gerding, E.; Sarne, D.; Shehory, O.

    2010-01-01

    We study different aspects of the multiagent resource allocation problem when the objective is to find an allocation that maximizes Nash social welfare, the product of the utilities of the individual agents. The Nash solution is an important welfare criterion that combines efficiency and fairness

  18. An analysis of multi-agent diagnosis

    NARCIS (Netherlands)

    Roos, Nico; Ten Teije, Annette; Bos, André; Witteveen, Cees; Castelfranchi, C.; Johnson, W.L.

    2002-01-01

    This paper analyzes the use of a Multi-Agent System for Model-Based Diagnosis. In a large dynamical system, it is often infeasible or even impossible to maintain a model of the whole system. Instead, several incomplete models of the system have to be used to establish a diagnosis and to detect

  19. Mansion, A Distributed Multi-Agent System

    NARCIS (Netherlands)

    van t Noordende, G.; Brazier, F.M.; Tanenbaum, A.S.

    2001-01-01

    In this position summary we present work in progress on a worldwide, scalable multi-agent system, based on a paradigm of hyperlinked rooms. The framework offers facilities for managing distribution, security and mobility aspects for both active elements (agents) and passive elements (objects) in the

  20. Event-Triggered Distributed Control of Nonlinear Interconnected Systems Using Online Reinforcement Learning With Exploration.

    Science.gov (United States)

    Narayanan, Vignesh; Jagannathan, Sarangapani

    2017-09-07

    In this paper, a distributed control scheme for an interconnected system composed of uncertain input affine nonlinear subsystems with event triggered state feedback is presented by using a novel hybrid learning scheme-based approximate dynamic programming with online exploration. First, an approximate solution to the Hamilton-Jacobi-Bellman equation is generated with event sampled neural network (NN) approximation and subsequently, a near optimal control policy for each subsystem is derived. Artificial NNs are utilized as function approximators to develop a suite of identifiers and learn the dynamics of each subsystem. The NN weight tuning rules for the identifier and event-triggering condition are derived using Lyapunov stability theory. Taking into account, the effects of NN approximation of system dynamics and boot-strapping, a novel NN weight update is presented to approximate the optimal value function. Finally, a novel strategy to incorporate exploration in online control framework, using identifiers, is introduced to reduce the overall cost at the expense of additional computations during the initial online learning phase. System states and the NN weight estimation errors are regulated and local uniformly ultimately bounded results are achieved. The analytical results are substantiated using simulation studies.

  1. An Active Learning Activity to Reinforce the Design Components of the Corticosteroids.

    Science.gov (United States)

    Slauson, Stephen R; Mandela, Prashant

    2018-02-05

    Despite the popularity of active learning applications over the past few decades, few activities have been reported for the field of medicinal chemistry. The purpose of this study is to report a new active learning activity, describe participant contributions, and examine participant performance on the assessment questions mapped to the objective covered by the activity. In this particular activity, students are asked to design two novel corticosteroids as a group (6-8 students per group) based on the design characteristics of marketed corticosteroids covered in lecture coupled with their pharmaceutics knowledge from the previous semester and then defend their design to the class through an interactive presentation model. Although class performance on the objective mapped to this material on the assessment did not reach statistical significance, use of this activity has allowed fruitful discussion of misunderstood concepts and facilitated multiple changes to the lecture presentation. As pharmacy schools continue to emphasize alternative learning pedagogies, publication of previously implemented activities demonstrating their use will help others apply similar methodologies.

  2. A Distributed Intelligent E-Learning System

    Science.gov (United States)

    Kristensen, Terje

    2016-01-01

    An E-learning system based on a multi-agent (MAS) architecture combined with the Dynamic Content Manager (DCM) model of E-learning, is presented. We discuss the benefits of using such a multi-agent architecture. Finally, the MAS architecture is compared with a pure service-oriented architecture (SOA). This MAS architecture may also be used within…

  3. Study on state grouping and opportunity evaluation for reinforcement learning methods; Kyoka gakushuho no tame no jotai grouping to opportunity hyoka ni kansuru kenkyu

    Energy Technology Data Exchange (ETDEWEB)

    Yu, W.; Yokoi, H.; Kakazu, Y. [Hokkaido University, Sapporo (Japan)

    1997-08-20

    In this paper, we propose the State Grouping scheme for coping with the problem of scaling up the Reinforcement Learning Algorithm to real, large size application. The grouping scheme is based on geographical and trial-error information, and is made up with state generating, state combining, state splitting, state forgetting procedures, with corresponding action selecting module and learning module. Also, we discuss the Labeling Based Evaluation scheme which can evaluate the opportunity of the state-action pair, therefore, use better experience to guide the exploration of the state-space effectively. Incorporating the Labeling Based Evaluation and State Grouping scheme into the Reinforcement Learning Algorithm, we get the approach that can generate organized state space for Reinforcement Learning, and do problem solving as well. We argue that the approach with this kind of ability is necessary for autonomous agent, namely, autonomous agent can not act depending on any pre-defined map, instead, it should search the environment as well as find the optimal problem solution autonomously and simultaneously. By solving the large state-size 3-DOF and 4-link manipulator problem, we show the efficiency of the proposed approach, i.e., the agent can achieve the optimal or sub-optimal path with less memory and less time. 14 refs., 11 figs., 3 tabs.

  4. Field tests applying multi-agent technology for distributed control. Virtual power plants and wind energy

    Energy Technology Data Exchange (ETDEWEB)

    Schaeffer, G.J.; Warmer, C.J.; Hommelberg, M.P.F.; Kamphuis, I.G.; Kok, J.K. [Energy in the Built Environment and Networks, Petten (Netherlands)

    2007-01-15

    Multi-agent technology is state of the art ICT. It is not yet widely applied in power control systems. However, it has a large potential for bottom-up, distributed control of a network with large-scale renewable energy sources (RES) and distributed energy resources (DER) in future power systems. At least two major European R and D projects (MicroGrids and CRISP) have investigated its potential. Both grid-related as well as market-related applications have been studied. This paper will focus on two field tests, performed in the Netherlands, applying multi-agent control by means of the PowerMatcher concept. The first field test focuses on the application of multi-agent technology in a commercial setting, i.e. by reducing the need for balancing power in the case of intermittent energy sources, such as wind energy. In this case the flexibility is used of demand and supply of industrial and residential consumers and producers. Imbalance reduction rates of over 40% have been achieved applying the PowerMatcher, and with a proper portfolio even larger rates are expected. In the second field test the multi-agent technology is used in the design and implementation of a virtual power plant (VPP). This VPP digitally connects a number of micro-CHP units, installed in residential dwellings, into a cluster that is controlled to reduce the local peak demand of the common low-voltage grid segment the micro-CHP units are connected to. In this way the VPP supports the local distribution system operator (DSO) to defer reinforcements in the grid infrastructure (substations and cables)

  5. Field tests applying multi-agent technology for distributed control. Virtual power plants and wind energy

    International Nuclear Information System (INIS)

    Schaeffer, G.J.; Warmer, C.J.; Hommelberg, M.P.F.; Kamphuis, I.G.; Kok, J.K.

    2007-01-01

    Multi-agent technology is state of the art ICT. It is not yet widely applied in power control systems. However, it has a large potential for bottom-up, distributed control of a network with large-scale renewable energy sources (RES) and distributed energy resources (DER) in future power systems. At least two major European R and D projects (MicroGrids and CRISP) have investigated its potential. Both grid-related as well as market-related applications have been studied. This paper will focus on two field tests, performed in the Netherlands, applying multi-agent control by means of the PowerMatcher concept. The first field test focuses on the application of multi-agent technology in a commercial setting, i.e. by reducing the need for balancing power in the case of intermittent energy sources, such as wind energy. In this case the flexibility is used of demand and supply of industrial and residential consumers and producers. Imbalance reduction rates of over 40% have been achieved applying the PowerMatcher, and with a proper portfolio even larger rates are expected. In the second field test the multi-agent technology is used in the design and implementation of a virtual power plant (VPP). This VPP digitally connects a number of micro-CHP units, installed in residential dwellings, into a cluster that is controlled to reduce the local peak demand of the common low-voltage grid segment the micro-CHP units are connected to. In this way the VPP supports the local distribution system operator (DSO) to defer reinforcements in the grid infrastructure (substations and cables)

  6. Multiagent Systems and Applications Volume 1Practice and Experience

    CERN Document Server

    Jain, Lakhmi

    2013-01-01

    The focus of the book is on completed implementations of agent-based software systems. Here, agent technology is considered broadly, starting from development of agent platforms, all the way through systems actually implemented. The covered topics also include lessons learned during implementation of agent platforms and the reflection on the process of development and application of agent-based systems.   The book includes 10 chapters where interested reader can find discussion of important issues encountered during development of well-known agent platforms such as JADE and Jadex as well as some interesting experiences in developing a new platform that combines software agent and Web Services. Furthermore, the book shows readers several valuable examples of applications based on multi-agent systems including simulations, agents in autonomous negotiations and agents in public administration modelling. We believe that the book will prove useful to the researchers, professors and the practitioners in all discip...

  7. MARS: An Educational Environment for Multiagent Robot Simulations

    Directory of Open Access Journals (Sweden)

    Marco Casini

    2016-01-01

    Full Text Available Undergraduate robotics students often find it difficult to design and validate control algorithms for teams of mobile robots. This is mainly due to two reasons. First, very rarely, educational laboratories are equipped with large teams of robots, which are usually expensive, bulky, and difficult to manage and maintain. Second, robotics simulators often require students to spend much time to learn their use and functionalities. For this purpose, a simulator of multiagent mobile robots named MARS has been developed within the Matlab environment, with the aim of helping students to simulate a wide variety of control algorithms in an easy way and without spending time for understanding a new language. Through this facility, the user is able to simulate multirobot teams performing different tasks, from cooperative to competitive ones, by using both centralized and distributed controllers. Virtual sensors are provided to simulate real devices. A graphical user interface allows students to monitor the robots behaviour through an online animation.

  8. A Reinforcement Learning Model Equipped with Sensors for Generating Perception Patterns: Implementation of a Simulated Air Navigation System Using ADS-B (Automatic Dependent Surveillance-Broadcast) Technology.

    Science.gov (United States)

    Álvarez de Toledo, Santiago; Anguera, Aurea; Barreiro, José M; Lara, Juan A; Lizcano, David

    2017-01-19

    Over the last few decades, a number of reinforcement learning techniques have emerged, and different reinforcement learning-based applications have proliferated. However, such techniques tend to specialize in a particular field. This is an obstacle to their generalization and extrapolation to other areas. Besides, neither the reward-punishment (r-p) learning process nor the convergence of results is fast and efficient enough. To address these obstacles, this research proposes a general reinforcement learning model. This model is independent of input and output types and based on general bioinspired principles that help to speed up the learning process. The model is composed of a perception module based on sensors whose specific perceptions are mapped as perception patterns. In this manner, similar perceptions (even if perceived at different positions in the environment) are accounted for by the same perception pattern. Additionally, the model includes a procedure that statistically associates perception-action pattern pairs depending on the positive or negative results output by executing the respective action in response to a particular perception during the learning process. To do this, the model is fitted with a mechanism that reacts positively or negatively to particular sensory stimuli in order to rate results. The model is supplemented by an action module that can be configured depending on the maneuverability of each specific agent. The model has been applied in the air navigation domain, a field with strong safety restrictions, which led us to implement a simulated system equipped with the proposed model. Accordingly, the perception sensors were based on Automatic Dependent Surveillance-Broadcast (ADS-B) technology, which is described in this paper. The results were quite satisfactory, and it outperformed traditional methods existing in the literature with respect to learning reliability and efficiency.

  9. Closed-loop adaptation of neurofeedback based on mental effort facilitates reinforcement learning of brain self-regulation.

    Science.gov (United States)

    Bauer, Robert; Fels, Meike; Royter, Vladislav; Raco, Valerio; Gharabaghi, Alireza

    2016-09-01

    Considering self-rated mental effort during neurofeedback may improve training of brain self-regulation. Twenty-one healthy, right-handed subjects performed kinesthetic motor imagery of opening their left hand, while threshold-based classification of beta-band desynchronization resulted in proprioceptive robotic feedback. The experiment consisted of two blocks in a cross-over design. The participants rated their perceived mental effort nine times per block. In the adaptive block, the threshold was adjusted on the basis of these ratings whereas adjustments were carried out at random in the other block. Electroencephalography was used to examine the cortical activation patterns during the training sessions. The perceived mental effort was correlated with the difficulty threshold of neurofeedback training. Adaptive threshold-setting reduced mental effort and increased the classification accuracy and positive predictive value. This was paralleled by an inter-hemispheric cortical activation pattern in low frequency bands connecting the right frontal and left parietal areas. Optimal balance of mental effort was achieved at thresholds significantly higher than maximum classification accuracy. Rating of mental effort is a feasible approach for effective threshold-adaptation during neurofeedback training. Closed-loop adaptation of the neurofeedback difficulty level facilitates reinforcement learning of brain self-regulation. Copyright © 2016 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

  10. Reinforcement-Learning-Based Robust Controller Design for Continuous-Time Uncertain Nonlinear Systems Subject to Input Constraints.

    Science.gov (United States)

    Liu, Derong; Yang, Xiong; Wang, Ding; Wei, Qinglai

    2015-07-01

    The design of stabilizing controller for uncertain nonlinear systems with control constraints is a challenging problem. The constrained-input coupled with the inability to identify accurately the uncertainties motivates the design of stabilizing controller based on reinforcement-learning (RL) methods. In this paper, a novel RL-based robust adaptive control algorithm is developed for a class of continuous-time uncertain nonlinear systems subject to input constraints. The robust control problem is converted to the constrained optimal control problem with appropriately selecting value functions for the nominal system. Distinct from typical action-critic dual networks employed in RL, only one critic neural network (NN) is constructed to derive the approximate optimal control. Meanwhile, unlike initial stabilizing control often indispensable in RL, there is no special requirement imposed on the initial control. By utilizing Lyapunov's direct method, the closed-loop optimal control system and the estimated weights of the critic NN are proved to be uniformly ultimately bounded. In addition, the derived approximate optimal control is verified to guarantee the uncertain nonlinear system to be stable in the sense of uniform ultimate boundedness. Two simulation examples are provided to illustrate the effectiveness and applicability of the present approach.

  11. Multi-Agent Systems for E-Commerce

    OpenAIRE

    Solodukha, T. V.; Sosnovskiy, O. A.; Zhelezko, B. A.

    2009-01-01

    The article focuses on multi-agent systems (MAS) and domains that can benefit from multi-agent technology. In the last few years, the agent based modeling (ABM) community has developed several practical agent based modeling toolkits that enable individuals to develop agent-based applications. The comparison of agent-based modeling toolkits is given. Multi-agent systems are designed to handle changing and dynamic business processes. Any organization with complex and distributed business pro...

  12. The role of multisensor data fusion in neuromuscular control of a sagittal arm with a pair of muscles using actor-critic reinforcement learning method.

    Science.gov (United States)

    Golkhou, V; Parnianpour, M; Lucas, C

    2004-01-01

    In this study, we consider the role of multisensor data fusion in neuromuscular control using an actor-critic reinforcement learning method. The model we use is a single link system actuated by a pair of muscles that are excited with alpha and gamma signals. Various physiological sensor information such as proprioception, spindle sensors, and Golgi tendon organs have been integrated to achieve an oscillatory movement with variable amplitude and frequency, while achieving a stable movement with minimum metabolic cost and coactivation. The system is highly nonlinear in all its physical and physiological attributes. Transmission delays are included in the afferent and efferent neural paths to account for a more accurate representation of the reflex loops. This paper proposes a reinforcement learning method with an Actor-Critic architecture instead of middle and low level of central nervous system (CNS). The Actor in this structure is a two layer feedforward neural network and the Critic is a model of the cerebellum. The Critic is trained by the State-Action-Reward-State-Action (SARSA) method. The Critic will train the Actor by supervisory learning based on previous experiences. The reinforcement signal in SARSA is evaluated based on available alternatives concerning the concept of multisensor data fusion. The effectiveness and the biological plausibility of the present model are demonstrated by several simulations. The system showed excellent tracking capability when we integrated the available sensor information. Addition of a penalty for activation of muscles resulted in much lower muscle coactivation while keeping the movement stable.

  13. Applications of Multi-Agent Technology to Power Systems

    Science.gov (United States)

    Nagata, Takeshi

    Currently, agents are focus of intense on many sub-fields of computer science and artificial intelligence. Agents are being used in an increasingly wide variety of applications. Many important computing applications such as planning, process control, communication networks and concurrent systems will benefit from using multi-agent system approach. A multi-agent system is a structure given by an environment together with a set of artificial agents capable to act on this environment. Multi-agent models are oriented towards interactions, collaborative phenomena, and autonomy. This article presents the applications of multi-agent technology to the power systems.

  14. Quantum-enhanced reinforcement learning for finite-episode games with discrete state spaces

    Science.gov (United States)

    Neukart, Florian; Von Dollen, David; Seidel, Christian; Compostella, Gabriele

    2017-12-01

    Quantum annealing algorithms belong to the class of metaheuristic tools, applicable for solving binary optimization problems. Hardware implementations of quantum annealing, such as the quantum annealing machines produced by D-Wave Systems, have been subject to multiple analyses in research, with the aim of characterizing the technology's usefulness for optimization and sampling tasks. Here, we present a way to partially embed both Monte Carlo policy iteration for finding an optimal policy on random observations, as well as how to embed n sub-optimal state-value functions for approximating an improved state-value function given a policy for finite horizon games with discrete state spaces on a D-Wave 2000Q quantum processing unit (QPU). We explain how both problems can be expressed as a quadratic unconstrained binary optimization (QUBO) problem, and show that quantum-enhanced Monte Carlo policy evaluation allows for finding equivalent or better state-value functions for a given policy with the same number episodes compared to a purely classical Monte Carlo algorithm. Additionally, we describe a quantum-classical policy learning algorithm. Our first and foremost aim is to explain how to represent and solve parts of these problems with the help of the QPU, and not to prove supremacy over every existing classical policy evaluation algorithm.

  15. The Curriculum-Faculty-Reinforcement Alignment and Its Effect on Learning Retention of Core Marketing Concepts of Marketing Capstone Students

    Science.gov (United States)

    Raska, David; Keller, Eileen Weisenbach; Shaw, Doris

    2014-01-01

    Curriculum-Faculty-Reinforcement (CFR) alignment is an alignment between fundamental marketing concepts that are integral to the mastery of knowledge expected of our marketing graduates, their perceived importance by the faculty, and their level of reinforcement throughout core marketing courses required to obtain a marketing degree. This research…

  16. Advanced Approach of Multiagent Based Buoy Communication.

    Science.gov (United States)

    Gricius, Gediminas; Drungilas, Darius; Andziulis, Arunas; Dzemydiene, Dale; Voznak, Miroslav; Kurmis, Mindaugas; Jakovlev, Sergej

    2015-01-01

    Usually, a hydrometeorological information system is faced with great data flows, but the data levels are often excessive, depending on the observed region of the water. The paper presents advanced buoy communication technologies based on multiagent interaction and data exchange between several monitoring system nodes. The proposed management of buoy communication is based on a clustering algorithm, which enables the performance of the hydrometeorological information system to be enhanced. The experiment is based on the design and analysis of the inexpensive but reliable Baltic Sea autonomous monitoring network (buoys), which would be able to continuously monitor and collect temperature, waviness, and other required data. The proposed approach of multiagent based buoy communication enables all the data from the costal-based station to be monitored with limited transition speed by setting different tasks for the agent-based buoy system according to the clustering information.

  17. Ontology-based multi-agent systems

    Energy Technology Data Exchange (ETDEWEB)

    Hadzic, Maja; Wongthongtham, Pornpit; Dillon, Tharam; Chang, Elizabeth [Digital Ecosystems and Business Intelligence Institute, Perth, WA (Australia)

    2009-07-01

    The Semantic web has given a great deal of impetus to the development of ontologies and multi-agent systems. Several books have appeared which discuss the development of ontologies or of multi-agent systems separately on their own. The growing interaction between agents and ontologies has highlighted the need for integrated development of these. This book is unique in being the first to provide an integrated treatment of the modeling, design and implementation of such combined ontology/multi-agent systems. It provides clear exposition of this integrated modeling and design methodology. It further illustrates this with two detailed case studies in (a) the biomedical area and (b) the software engineering area. The book is, therefore, of interest to researchers, graduate students and practitioners in the semantic web and web science area. (orig.)

  18. Advanced Approach of Multiagent Based Buoy Communication

    Directory of Open Access Journals (Sweden)

    Gediminas Gricius

    2015-01-01

    Full Text Available Usually, a hydrometeorological information system is faced with great data flows, but the data levels are often excessive, depending on the observed region of the water. The paper presents advanced buoy communication technologies based on multiagent interaction and data exchange between several monitoring system nodes. The proposed management of buoy communication is based on a clustering algorithm, which enables the performance of the hydrometeorological information system to be enhanced. The experiment is based on the design and analysis of the inexpensive but reliable Baltic Sea autonomous monitoring network (buoys, which would be able to continuously monitor and collect temperature, waviness, and other required data. The proposed approach of multiagent based buoy communication enables all the data from the costal-based station to be monitored with limited transition speed by setting different tasks for the agent-based buoy system according to the clustering information.

  19. Network Management using Multi-Agents System

    Directory of Open Access Journals (Sweden)

    Nestor DUQUE

    2013-07-01

    Full Text Available This paper aims to present a multiagent system for network management. The models developed for the proposed system defines certain intelligent agents interact to achieve the objectives and requirements of the multiagent organization.These agents have the property of being adaptive, acquire knowledge and skills to make decisions according to the actual state of the network that is represented in the information base, MIB, SNMP devices. The ideal state of the network policy is defined by the end user entered, which contain the value that should have performance variables and other parameters such as the frequency with which these variables should be monitored.. An agent based architecture increase the integration, adaptability, cooperation, autonomy and the efficient operation in heterogeneous environment in the network supervision. 

  20. Network Management using Multi-Agents System

    Directory of Open Access Journals (Sweden)

    Gustavo ISAZA

    2012-12-01

    Full Text Available This paper aims to present a multiagent system for network management. The models developed for the proposed system defines certain intelligent agents interact to achieve the objectives and requirements of the multiagent organization.These agents have the property of being adaptive, acquire knowledge and skills to make decisions according to the actual state of the network that is represented in the information base, MIB, SNMP devices. The ideal state of the network policy is defined by the end user entered, which contain the value that should have performance variables and other parameters such as the frequency with which these variables should be monitored.. An agent based architecture increase the integration, adaptability, cooperation, autonomy and the efficient operation in heterogeneous environment in the network supervision. 

  1. Autonomous Formations of Multi-Agent Systems

    Science.gov (United States)

    Dhali, Sanjana; Joshi, Suresh M.

    2013-01-01

    Autonomous formation control of multi-agent dynamic systems has a number of applications that include ground-based and aerial robots and satellite formations. For air vehicles, formation flight ("flocking") has the potential to significantly increase airspace utilization as well as fuel efficiency. This presentation addresses two main problems in multi-agent formations: optimal role assignment to minimize the total cost (e.g., combined distance traveled by all agents); and maintaining formation geometry during flock motion. The Kuhn-Munkres ("Hungarian") algorithm is used for optimal assignment, and consensus-based leader-follower type control architecture is used to maintain formation shape despite the leader s independent movements. The methods are demonstrated by animated simulations.

  2. Multiagent-Based Model For ESCM

    Directory of Open Access Journals (Sweden)

    Delia MARINCAS

    2011-01-01

    Full Text Available Web based applications for Supply Chain Management (SCM are now a necessity for every company in order to meet the increasing customer demands, to face the global competition and to make profit. Multiagent-based approach is appropriate for eSCM because it shows many of the characteristics a SCM system should have. For this reason, we have proposed a multiagent-based eSCM model which configures a virtual SC, automates the SC activities: selling, purchasing, manufacturing, planning, inventory, etc. This model will allow a better coordination of the supply chain network and will increase the effectiveness of Web and intel-ligent technologies employed in eSCM software.

  3. The Patient Educator Presentation in Dental Education: Reinforcing the Importance of Learning About Rare Conditions.

    Science.gov (United States)

    Edwards, Paul C; Graham, Jasmine; Oling, Rebecca; Frantz, Kate E

    2016-05-01

    The aim of this study was to determine whether a patient educator presentation (PEP) on pemphigus vulgaris would increase second-year dental students' awareness of the importance of learning about rare conditions and improve their retention of rare disease knowledge. The study involved students' subjective assessments of a PEP experience at two U.S. dental schools. In this mixed methods study, cross-sectional data were obtained by surveys and in-depth interviews. Questions focused on students' assessment of the messages acquired from the PEP and its likely impact on their future clinical care. At University 1, students completed paper surveys with open-ended questions and participated in a focus group. At University 2, students completed an online survey consisting of rating scale and open-ended questions. Responses to open-ended questions were categorized into themes. At University 1, 79 students (out of a possible 102; response rate 77.5%) completed the survey, and an additional ten students participated in a focus group. At University 2, 30 students (out of a possible 104; response rate 28.8%) completed the survey. At Universities 1 and 2, 88% and 100%, respectively, of respondents stated the PEP would influence their future clinical decision making. The vast majority of respondents (94% and 100% at University 1 and University 2, respectively) were of the opinion that the personal testimonial from a patient would help them recall information about pemphigus vulgaris in five years' time. Respondents from both universities commented that the PEP emphasized the importance of not dismissing a patient's concerns. These results suggest that a presentation by a patient with a rare condition can be an effective educational tool for preclinical dental students.

  4. The Multi-Agent Transport Simulation MATSim

    OpenAIRE

    Horni Andreas; Nagel Kai; Axhausen Kay W.

    2016-01-01

    "The MATSim (Multi-Agent Transport Simulation) software project was started around 2006 with the goal of generating traffic and congestion patterns by following individual synthetic travelers through their daily or weekly activity programme. It has since then evolved from a collection of stand-alone C++ programs to an integrated Java-based framework which is publicly hosted, open-source available, automatically regression tested. It is currently used by about 40 groups throughout the world. T...

  5. A Multi-Agent Based Energy Management Solution for Integrated Buildings and Microgrid System

    DEFF Research Database (Denmark)

    Anvari-Moghaddam, Amjad; Rahimi-Kian, Ashkan; Mirian, Maryam S.

    2017-01-01

    -reflex to complex learning agents are designed and implemented to cooperate with each other to reach an optimal operating strategy for the mentioned integrated energy system (IES) while meeting the system’s objectives and related constraints. The optimization process for the EMS is defined as a coordinated......In this paper, an ontology-driven multi-agent based energy management system (EMS) is proposed for monitoring and optimal control of an integrated homes/buildings and microgrid system with various renewable energy resources (RESs) and controllable loads. Different agents ranging from simple...... distributed generation (DG) and demand response (DR) management problem within the studied environment and is solved by the proposed agent-based approach utilizing cooperation and communication among decision agents. To verify the effectiveness and applicability of the proposed multi-agent based EMS, several...

  6. Depression, Activity, and Evaluation of Reinforcement

    Science.gov (United States)

    Hammen, Constance L.; Glass, David R., Jr.

    1975-01-01

    This research attempted to find the causal relation between mood and level of reinforcement. An effort was made to learn what mood change might occur if depressed subjects increased their levels of participation in reinforcing activities. (Author/RK)

  7. Development of Reinforcement Learning Algorithm for Automation of Slide Gate Check Structure in Canals

    Directory of Open Access Journals (Sweden)

    K. Shahverdi

    2016-02-01

    Full Text Available Introduction: Nowadays considering water shortage and weak management in agricultural water sector and for optimal uses of water, irrigation networks performance need to be improveed. Recently, intelligent management of water conveyance and delivery, and better control technologies have been considered for improving the performance of irrigation networks and their operation. For this affair, providing of mathematical model of automatic control system and related structures, which connected with hydrodynamic models, is necessary. The main objective of this research, is development of mathematical model of RL upstream control algorithm inside ICSS hydrodynamic model as a subroutine. Materials and Methods: In the learning systems, a set of state-action rules called classifiers compete to control the system based on the system's receipt from the environment. One could be identified five main elements of the RL: an agent, an environment, a policy, a reward function, and a simulator. The learner (decision-maker is called the agent. The thing it interacts with, comprising everything outside the agent, is called the environment. The agent selects an action based on existing state in the environment. When the agent takes an action and performs on environment, the environment goes new state and reward is assigned based on it. The agent and the environment continually interact to maximize the reward. The policy is a set of state-action pair, which have higher rewards. It defines the agent's behavior and says which action must be taken in which state. The reward function defines the goal in a RL problem. The reward function defines what the good and bad events are for the agent. The higher the reward, the better the action. The simulator provides environment information. In irrigation canals, the agent is the check structures. The action and state are the check structures adjustment and the water depth, respectively. The environment comprises the hydraulic

  8. Punishment and psychopathy: a case-control functional MRI investigation of reinforcement learning in violent antisocial personality disordered men.

    Science.gov (United States)

    Gregory, Sarah; Blair, R James; Ffytche, Dominic; Simmons, Andrew; Kumari, Veena; Hodgins, Sheilagh; Blackwood, Nigel

    2015-02-01

    Men with antisocial personality disorder show lifelong abnormalities in adaptive decision making guided by the weighing up of reward and punishment information. Among men with antisocial personality disorder, modification of the behaviour of those with additional diagnoses of psychopathy seems particularly resistant to punishment. We did a case-control functional MRI (fMRI) study in 50 men, of whom 12 were violent offenders with antisocial personality disorder and psychopathy, 20 were violent offenders with antisocial personality disorder but not psychopathy, and 18 were healthy non-offenders. We used fMRI to measure brain activation associated with the representation of punishment or reward information during an event-related probabilistic response-reversal task, assessed with standard general linear-model-based analysis. Offenders with antisocial personality disorder and psychopathy displayed discrete regions of increased activation in the posterior cingulate cortex and anterior insula in response to punished errors during the task reversal phase, and decreased activation to all correct rewarded responses in the superior temporal cortex. This finding was in contrast to results for offenders without psychopathy and healthy non-offenders. Punishment prediction error signalling in offenders with antisocial personality disorder and psychopathy was highly atypical. This finding challenges the widely held view that such men are simply characterised by diminished neural sensitivity to punishment. Instead, this finding indicates altered organisation of the information-processing system responsible for reinforcement learning and appropriate decision making. This difference between violent offenders with antisocial personality disorder with and without psychopathy has implications for the causes of these disorders and for treatment approaches. National Forensic Mental Health Research and Development Programme, UK Ministry of Justice, Psychiatry Research Trust, NIHR

  9. A confidence metric for using neurobiological feedback in actor-critic reinforcement learning based brain-machine interfaces

    Directory of Open Access Journals (Sweden)

    Noeline Wilhelmina Prins

    2014-05-01

    Full Text Available Brain-Machine Interfaces (BMIs can be used to restore function in people living with paralysis. Current BMIs require extensive calibration that increase the set-up times and external inputs for decoder training that may be difficult to produce in paralyzed individuals. Both these factors have presented challenges in transitioning the technology from research environments to activities of daily living (ADL. For BMIs to be seamlessly used in ADL, these issues should be handled with minimal external input thus reducing the need for a technician/caregiver to calibrate the system. Reinforcement Learning (RL based BMIs are a good tool to be used when there is no external training signal and can provide an adaptive modality to train BMI decoders. However, RL based BMIs are sensitive to the feedback provided to adapt the BMI. In actor-critic BMIs, this feedback is provided by the critic and the overall system performance is limited by the critic accuracy. In this work, we developed an adaptive BMI that could handle inaccuracies in the critic feedback in an effort to produce more accurate RL based BMIs. We developed a confidence measure, which indicated how appropriate the feedback is for updating the decoding parameters of the actor. The results show that with the new update formulation, the critic accuracy is no longer a limiting factor for the overall performance. We tested and validated the system on three different data sets: synthetic data generated by an Izhikevich neural spiking model, synthetic data with a Gaussian noise distribution, and data collected from a non-human primate engaged in a reaching task. All results indicated that the system with the critic confidence built in always outperformed the system without the critic confidence. Results of this study suggest the potential application of the technique in developing an autonomous BMI that does not need an external signal for training or extensive calibration.

  10. AN EXTENDED REINFORCEMENT LEARNING MODEL OF BASAL GANGLIA TO UNDERSTAND THE CONTRIBUTIONS OF SEROTONIN AND DOPAMINE IN RISK-BASED DECISION MAKING, REWARD PREDICTION, AND PUNISHMENT LEARNING

    Directory of Open Access Journals (Sweden)

    Pragathi Priyadharsini Balasubramani

    2014-04-01

    Full Text Available Although empirical and neural studies show that serotonin (5HT plays many functional roles in the brain, prior computational models mostly focus on its role in behavioral inhibition. In this study, we present a model of risk based decision making in a modified Reinforcement Learning (RL-framework. The model depicts the roles of dopamine (DA and serotonin (5HT in Basal Ganglia (BG. In this model, the DA signal is represented by the temporal difference error (δ, while the 5HT signal is represented by a parameter (α that controls risk prediction error. This formulation that accommodates both 5HT and DA reconciles some of the diverse roles of 5HT particularly in connection with the BG system. We apply the model to different experimental paradigms used to study the role of 5HT: 1 Risk-sensitive decision making, where 5HT controls risk assessment, 2 Temporal reward prediction, where 5HT controls time-scale of reward prediction, and 3 Reward/Punishment sensitivity, in which the punishment prediction error depends on 5HT levels. Thus the proposed integrated RL model reconciles several existing theories of 5HT and DA in the BG.

  11. A reusable multi-agent architecture for active intelligent websites

    NARCIS (Netherlands)

    Jonker, C.M.; Lam, R.A.; Treur, J.

    In this paper a reusable multi-agent architecture for intelligent Websites is presented and illustrated for an electronic department store. The architecture has been designed and implemented using the compositional design method for multi-agent systems DESIRE. The agents within this architecture are

  12. Quality Care through Multi-Age Grouping of Children.

    Science.gov (United States)

    Prendergast, Leo

    2002-01-01

    Asserts that multi-age grouping in early childhood settings can and does work. Addresses four main hurdles to successful implementation: (1) laws and regulations that act as barriers; (2) health concerns; (3) overcoming educational values that conflict with those of the age-grouped classroom; and (4) staff misunderstanding of multi-age grouping…

  13. Multi-Agent Modeling in Managing Six Sigma Projects

    Directory of Open Access Journals (Sweden)

    K. Y. Chau

    2009-10-01

    Full Text Available In this paper, a multi-agent model is proposed for considering the human resources factor in decision making in relation to the six sigma project. The proposed multi-agent system is expected to increase the acccuracy of project prioritization and to stabilize the human resources service level. A simulation of the proposed multiagent model is conducted. The results show that a multi-agent model which takes into consideration human resources when making decisions about project selection and project team formation is important in enabling efficient and effective project management. The multi-agent modeling approach provides an alternative approach for improving communication and the autonomy of six sigma projects in business organizations.

  14. A review of norms and normative multiagent systems.

    Science.gov (United States)

    Mahmoud, Moamin A; Ahmad, Mohd Sharifuddin; Yusoff, Mohd Zaliman Mohd; Mustapha, Aida

    2014-01-01

    Norms and normative multiagent systems have become the subjects of interest for many researchers. Such interest is caused by the need for agents to exploit the norms in enhancing their performance in a community. The term norm is used to characterize the behaviours of community members. The concept of normative multiagent systems is used to facilitate collaboration and coordination among social groups of agents. Many researches have been conducted on norms that investigate the fundamental concepts, definitions, classification, and types of norms and normative multiagent systems including normative architectures and normative processes. However, very few researches have been found to comprehensively study and analyze the literature in advancing the current state of norms and normative multiagent systems. Consequently, this paper attempts to present the current state of research on norms and normative multiagent systems and propose a norm's life cycle model based on the review of the literature. Subsequently, this paper highlights the significant areas for future work.

  15. A Review of Norms and Normative Multiagent Systems

    Science.gov (United States)

    Mahmoud, Moamin A.; Ahmad, Mohd Sharifuddin; Mustapha, Aida

    2014-01-01

    Norms and normative multiagent systems have become the subjects of interest for many researchers. Such interest is caused by the need for agents to exploit the norms in enhancing their performance in a community. The term norm is used to characterize the behaviours of community members. The concept of normative multiagent systems is used to facilitate collaboration and coordination among social groups of agents. Many researches have been conducted on norms that investigate the fundamental concepts, definitions, classification, and types of norms and normative multiagent systems including normative architectures and normative processes. However, very few researches have been found to comprehensively study and analyze the literature in advancing the current state of norms and normative multiagent systems. Consequently, this paper attempts to present the current state of research on norms and normative multiagent systems and propose a norm's life cycle model based on the review of the literature. Subsequently, this paper highlights the significant areas for future work. PMID:25110739

  16. Multiagent data warehousing and multiagent data mining for cerebrum/cerebellum modeling

    Science.gov (United States)

    Zhang, Wen-Ran

    2002-03-01

    An algorithm named Neighbor-Miner is outlined for multiagent data warehousing and multiagent data mining. The algorithm is defined in an evolving dynamic environment with autonomous or semiautonomous agents. Instead of mining frequent itemsets from customer transactions, the new algorithm discovers new agents and mining agent associations in first-order logic from agent attributes and actions. While the Apriori algorithm uses frequency as a priory threshold, the new algorithm uses agent similarity as priory knowledge. The concept of agent similarity leads to the notions of agent cuboid, orthogonal multiagent data warehousing (MADWH), and multiagent data mining (MADM). Based on agent similarities and action similarities, Neighbor-Miner is proposed and illustrated in a MADWH/MADM approach to cerebrum/cerebellum modeling. It is shown that (1) semiautonomous neurofuzzy agents can be identified for uniped locomotion and gymnastic training based on attribute relevance analysis; (2) new agents can be discovered and agent cuboids can be dynamically constructed in an orthogonal MADWH, which resembles an evolving cerebrum/cerebellum system; and (3) dynamic motion laws can be discovered as association rules in first order logic. Although examples in legged robot gymnastics are used to illustrate the basic ideas, the new approach is generally suitable for a broad category of data mining tasks where knowledge can be discovered collectively by a set of agents from a geographically or geometrically distributed but relevant environment, especially in scientific and engineering data environments.

  17. 9th KES Conference on Agent and Multi-Agent Systems : Technologies and Applications

    CERN Document Server

    Howlett, Robert; Jain, Lakhmi

    2015-01-01

    Agents and multi-agent systems are related to a modern software paradigm which has long been recognized as a promising technology for constructing autonomous, complex and intelligent systems. The topics covered in this volume include agent-oriented software engineering, agent co-operation, co-ordination, negotiation, organization and communication, distributed problem solving, specification of agent communication languages, agent privacy, safety and security, formalization of ontologies and conversational agents. The volume highlights new trends and challenges in agent and multi-agent research and includes 38 papers classified in the following specific topics: learning paradigms, agent-based modeling and simulation, business model innovation and disruptive technologies, anthropic-oriented computing, serious games and business intelligence, design and implementation of intelligent agents and multi-agent systems, digital economy, and advances in networked virtual enterprises. Published p...

  18. Reinforcing Saccadic Amplitude Variability

    Science.gov (United States)

    Paeye, Celine; Madelain, Laurent

    2011-01-01

    Saccadic endpoint variability is often viewed as the outcome of neural noise occurring during sensorimotor processing. However, part of this variability might result from operant learning. We tested this hypothesis by reinforcing dispersions of saccadic amplitude distributions, while maintaining constant their medians. In a first experiment we…

  19. Deep Reinforcement Fuzzing

    OpenAIRE

    Böttinger, Konstantin; Godefroid, Patrice; Singh, Rishabh

    2018-01-01

    Fuzzing is the process of finding security vulnerabilities in input-processing code by repeatedly testing the code with modified inputs. In this paper, we formalize fuzzing as a reinforcement learning problem using the concept of Markov decision processes. This in turn allows us to apply state-of-the-art deep Q-learning algorithms that optimize rewards, which we define from runtime properties of the program under test. By observing the rewards caused by mutating with a specific set of actions...

  20. Dynamic Resource Allocation with Integrated Reinforcement Learning for a D2D-Enabled LTE-A Network with Access to Unlicensed Band

    Directory of Open Access Journals (Sweden)

    Alia Asheralieva

    2016-01-01

    Full Text Available We propose a dynamic resource allocation algorithm for device-to-device (D2D communication underlying a Long Term Evolution Advanced (LTE-A network with reinforcement learning (RL applied for unlicensed channel allocation. In a considered system, the inband and outband resources are assigned by the LTE evolved NodeB (eNB to different device pairs to maximize the network utility subject to the target signal-to-interference-and-noise ratio (SINR constraints. Because of the absence of an established control link between the unlicensed and cellular radio interfaces, the eNB cannot acquire any information about the quality and availability of unlicensed channels. As a result, a considered problem becomes a stochastic optimization problem that can be dealt with by deploying a learning theory (to estimate the random unlicensed channel environment. Consequently, we formulate the outband D2D access as a dynamic single-player game in which the player (eNB estimates its possible strategy and expected utility for all of its actions based only on its own local observations using a joint utility and strategy estimation based reinforcement learning (JUSTE-RL with regret algorithm. A proposed approach for resource allocation demonstrates near-optimal performance after a small number of RL iterations and surpasses the other comparable methods in terms of energy efficiency and throughput maximization.

  1. Effectiveness of an educational video as an instrument to refresh and reinforce the learning of a nursing technique: a randomized controlled trial.

    Science.gov (United States)

    Salina, Loris; Ruffinengo, Carlo; Garrino, Lorenza; Massariello, Patrizia; Charrier, Lorena; Martin, Barbara; Favale, Maria Santina; Dimonte, Valerio

    2012-05-01

    The Undergraduate Nursing Course has been using videos for the past year or so. Videos are used for many different purposes such as during lessons, nurse refresher courses, reinforcement, and sharing and comparison of knowledge with the professional and scientific community. The purpose of this study was to estimate the efficacy of the video (moving an uncooperative patient from the supine to the lateral position) as an instrument to refresh and reinforce nursing techniques. A two-arm randomized controlled trial (RCT) design was chosen: both groups attended lessons in the classroom as well as in the laboratory; a month later while one group received written information as a refresher, the other group watched the video. Both groups were evaluated in a blinded fashion. A total of 223 students agreed to take part in the study. The difference observed between those who had seen the video and those who had read up on the technique turned out to be an average of 6.19 points in favour of the first (P video were better able to apply the technique, resulting in a better performance. The video, therefore, represents an important tool to refresh and reinforce previous learning.

  2. Analysis of Bullying in Cooperative Multi-agent Systems’ Communications

    Directory of Open Access Journals (Sweden)

    Celia Gutiérrez

    2013-12-01

    Full Text Available Cooperative Multi-agent Systems frameworks do not include modules to test communications yet. The proposed framework incorporates robust analysis tools using IDKAnalysis2.0 to evaluate bullying effect in communications. The present work is based on ICARO-T. This platform follows the Adaptive Multi-agent Systems paradigm. Experimentation with ICARO-T includes two deployments: the equitative and the authoritative. Results confirm the usefulness of the analysis tools when exporting to Cooperative Multi-agent Systems that use different configurations. Besides, ICARO-T is provided with new functionality by a set of tools for communication analysis.

  3. Predictive Control of Networked Multiagent Systems via Cloud Computing.

    Science.gov (United States)

    Liu, Guo-Ping

    2017-01-18

    This paper studies the design and analysis of networked multiagent predictive control systems via cloud computing. A cloud predictive control scheme for networked multiagent systems (NMASs) is proposed to achieve consensus and stability simultaneously and to compensate for network delays actively. The design of the cloud predictive controller for NMASs is detailed. The analysis of the cloud predictive control scheme gives the necessary and sufficient conditions of stability and consensus of closed-loop networked multiagent control systems. The proposed scheme is verified to characterize the dynamical behavior and control performance of NMASs through simulations. The outcome provides a foundation for the development of cooperative and coordinative control of NMASs and its applications.

  4. Believer-Skeptic Meets Actor-Critic: Rethinking the Role of Basal Ganglia Pathways during Decision-Making and Reinforcement Learning

    Science.gov (United States)

    Dunovan, Kyle; Verstynen, Timothy

    2016-01-01

    The flexibility of behavioral control is a testament to the brain's capacity for dynamically resolving uncertainty during goal-directed actions. This ability to select actions and learn from immediate feedback is driven by the dynamics of basal ganglia (BG) pathways. A growing body of empirical evidence conflicts with the traditional view that these pathways act as independent levers for facilitating (i.e., direct pathway) or suppressing (i.e., indirect pathway) motor output, suggesting instead that they engage in a dynamic competition during action decisions that computationally captures action uncertainty. Here we discuss the utility of encoding action uncertainty as a dynamic competition between opposing control pathways and provide evidence that this simple mechanism may have powerful implications for bridging neurocomputational theories of decision making and reinforcement learning. PMID:27047328

  5. Multi-Agent Information Classification Using Dynamic Acquaintance Lists.

    Science.gov (United States)

    Mukhopadhyay, Snehasis; Peng, Shengquan; Raje, Rajeev; Palakal, Mathew; Mostafa, Javed

    2003-01-01

    Discussion of automated information services focuses on information classification and collaborative agents, i.e. intelligent computer programs. Highlights include multi-agent systems; distributed artificial intelligence; thesauri; document representation and classification; agent modeling; acquaintances, or remote agents discovered through…

  6. Adaptive learning in agents behaviour: A framework for electricity markets simulation

    DEFF Research Database (Denmark)

    Pinto, Tiago; Vale, Zita; Sousa, Tiago M.

    2014-01-01

    decision support to MASCEM's negotiating agents so that they can properly achieve their goals. ALBidS uses artificial intelligence methodologies and data analysis algorithms to provide effective adaptive learning capabilities to such negotiating entities. The main contribution is provided by a methodology...... that combines several distinct strategies to build actions proposals, so that the best can be chosen at each time, depending on the context and simulation circumstances. The choosing process includes reinforcement learning algorithms, a mechanism for negotiating contexts analysis, a mechanism for the management...... allows integrating different strategic approaches for electricity market negotiations, and choosing the most appropriate one at each time, for each different negotiation context. This methodology is integrated in ALBidS (Adaptive Learning strategic Bidding System) – a multiagent system that provides...

  7. Distributed Optimal Consensus Control for Multiagent Systems With Input Delay.

    Science.gov (United States)

    Zhang, Huaipin; Yue, Dong; Zhao, Wei; Hu, Songlin; Dou, Chunxia; Huaipin Zhang; Dong Yue; Wei Zhao; Songlin Hu; Chunxia Dou; Hu, Songlin; Zhang, Huaipin; Dou, Chunxia; Yue, Dong; Zhao, Wei

    2018-06-01

    This paper addresses the problem of distributed optimal consensus control for a continuous-time heterogeneous linear multiagent system subject to time varying input delays. First, by discretization and model transformation, the continuous-time input-delayed system is converted into a discrete-time delay-free system. Two delicate performance index functions are defined for these two systems. It is shown that the performance index functions are equivalent and the optimal consensus control problem of the input-delayed system can be cast into that of the delay-free system. Second, by virtue of the Hamilton-Jacobi-Bellman (HJB) equations, an optimal control policy for each agent is designed based on the delay-free system and a novel value iteration algorithm is proposed to learn the solutions to the HJB equations online. The proposed adaptive dynamic programming algorithm is implemented on the basis of a critic-action neural network (NN) structure. Third, it is proved that local consensus errors of the two systems and weight estimation errors of the critic-action NNs are uniformly ultimately bounded while the approximated control policies converge to their target values. Finally, two simulation examples are presented to illustrate the effectiveness of the developed method.

  8. A Framework for Normative MultiAgent Organisations

    OpenAIRE

    Boissier, Olivier; Hübner, Jomi Fred

    2009-01-01

    The social and organisational aspects of agency have led to a good amount of theoretical work in terms of formal models and theories. From these different works normative multiagent systems and multiagent organisations are particularily considered in this paper. Embodying such models and theories in the conception and engineering of proper infrastructures that achieve requirements of openness and adaptation, is still an open issue. In this direction, this paper presents and discusses a framew...

  9. NADIM-Travel: A Multiagent Platform for Travel Services Aggregation

    OpenAIRE

    Ben Ameur, Houssein; Bédard, François; Vaucher, Stéphane; Kropf, Peter; Chaib-draaa, Brahim; Gérin-Lajoie, Robert

    2010-01-01

    With the Internet as a growing channel for travel services distribution, sophisticated travel services aggregators are increasingly in demand. A travel services aggregation platform should be able to manage the heterogeneous characteristics of the many existing travel services. It should also be as scalable, robust, and flexible as possible. Using multiagent technology, we designed and implemented a multiagent platform for travel services aggregation called NADIM-Travel. In this platform, a p...

  10. Planning of Autonomous Multi-agent Intersection

    Directory of Open Access Journals (Sweden)

    Viksnin Ilya I.

    2016-01-01

    Full Text Available In this paper, we propose a traffic management system with agents acting on behalf autonomous vehicle at the crossroads. Alternatively to existing solutions based on usage of semiautonomous control systems with the control unit, proposed in this paper algorithm apply the principles of decentralized multi-agent control. Agents during their collaboration generate intersection plan and determinate the optimal order of road intersection for a given criterion based on the exchange of information about them and their environment. The paper contains optimization criteria for possible routes selection and experiments that perform in order to estimate the proposed model. Experiment results show that this model can significantly reduce traffic density compared to the traditional traffic management systems. Moreover, the proposed algorithm efficiency increases with road traffic density. Furthermore, the availability of control unit in the system significantly reduces the negative impact of possible failures and hacker attacks.

  11. Regulated open multi-agent systems (ROMAS) a multi-agent approach for designing normative open systems

    CERN Document Server

    Garcia, Emilia; Botti, Vicente

    2015-01-01

    Addressing the open problem of engineering normative open systems using the multi-agent paradigm, normative open systems are explained as systems in which heterogeneous and autonomous entities and institutions coexist in a complex social and legal framework that can evolve to address the different and often conflicting objectives of the many stakeholders involved. Presenting  a software engineering approach which covers both the analysis and design of these kinds of systems, and which deals with the open issues in the area, ROMAS (Regulated Open Multi-Agent Systems) defines a specific multi-agent architecture, meta-model, methodology and CASE tool. This CASE tool is based on Model-Driven technology and integrates the graphical design with the formal verification of some properties of these systems by means of model checking techniques. Utilizing tables to enhance reader insights into the most important requirements for designing normative open multi-agent systems, the book also provides a detailed and easy t...

  12. Will Increasing Academic Recognition of Workplace Learning in the UK Reinforce Existing Gender Divisions in the Labour Market?

    Science.gov (United States)

    Walsh, Anita

    2006-01-01

    In the United Kingdom there has been a considerable increase in the academic recognition of workplace learning, and a number of new awards drawing on workplace learning have been introduced. These include apprenticeships and Advanced Apprenticeships, both of which contain National Vocational Qualifications, and the Foundation Degree. In addition,…

  13. A Multi-Agent System for Tracking the Intent of Surface Contacts in Ports and Waterways

    National Research Council Canada - National Science Library

    Tan, Kok S

    2005-01-01

    ...) and employ them to identify asymmetric maritime threats in port and waterways. Each surface track is monitored by a compound multi-agent system that comprise of the several intent models, each containing a nested multi-agent system...

  14. Specification of Behavioural Requirements within Compositional Multi-Agent System Design

    OpenAIRE

    Herlea, D.E.; Jonker, C.M.; Treur, J.; Wijngaards, N.J.E.

    1999-01-01

    In this paper it is shown how informal and formal specification of behavioural requirements and scenarios for agents and multi-agent systems can be integrated within multi-agent system design. In particular, it is addressed how a compositional

  15. Examining Play among Young Children in Single-Age and Multi-Age Preschool Classroom Settings

    Science.gov (United States)

    Youhne, Mia Song

    2009-01-01

    Advocates for multi-age classrooms claim multi-age groupings benefit children (Brynes, Shuster, & Jones, 1994). Currently, there is a lack of research examining play among students in multi-age classrooms. If indeed there is a positive benefit of play among children, research is needed to examine these behaviors among and between young children in…

  16. Applying Activity Theory in Multiagency Settings

    Directory of Open Access Journals (Sweden)

    Daniels H.,

    2016-12-01

    Full Text Available In this paper I explore the extent to which two approaches to the social formation of mind are compatible and may be used to enrich and extend each other. These are: Activity Theory (AT as derived from the work of the early Russian psychologists, Vygotsky and Leontiev, and the work of the sociologist Basil Bernstein. The purpose is to show how Bernstein provides a language of description which allows Vygotsky’s account of social formation of mind to be extended and enhanced through an understanding of the sociological processes which form specific modalities of pedagogic practice and their specialized scientific concepts. The two approaches engage with a common theme namely the social shaping of consciousness, from different perspectives and yet as Bernstein acknowledges both develop many of their core assumptions from the work of Marx and the French school of early twentieth century sociology. The work of the Russian linguist is also be used to further nuance the argument applied in multiagency settings.

  17. Multi-Agent Cooperative Target Search

    Directory of Open Access Journals (Sweden)

    Jinwen Hu

    2014-05-01

    Full Text Available This paper addresses a vision-based cooperative search for multiple mobile ground targets by a group of unmanned aerial vehicles (UAVs with limited sensing and communication capabilities. The airborne camera on each UAV has a limited field of view and its target discriminability varies as a function of altitude. First, by dividing the whole surveillance region into cells, a probability map can be formed for each UAV indicating the probability of target existence within each cell. Then, we propose a distributed probability map updating model which includes the fusion of measurement information, information sharing among neighboring agents, information decay and transmission due to environmental changes such as the target movement. Furthermore, we formulate the target search problem as a multi-agent cooperative coverage control problem by optimizing the collective coverage area and the detection performance. The proposed map updating model and the cooperative control scheme are distributed, i.e., assuming that each agent only communicates with its neighbors within its communication range. Finally, the effectiveness of the proposed algorithms is illustrated by simulation.

  18. Control Prosody using Multi-Agent System

    Directory of Open Access Journals (Sweden)

    Kenji MATSUI

    2014-03-01

    Full Text Available Persons who have undergone a laryngectomy have a few options to partially restore speech but no completely satisfactory device. Even though the use of an electrolarynx (EL is the easiest way for a patient to produce speech, it does not produce a natural tone and appearance is far from normal. Because of that and the fact that none of them are hands-free, the feasibility of using a motion sensor to replace a conventional EL user interface has been explored. A mobile device motion sensor with multi-agent platform has been used to investigate on/off and pitch frequency control capability. A very small battery operated ARM-based control unit has also been developed to evaluate the motion sensor based user-interface. This control unit is placed on the wrist and the vibration device against the throat using support bandage. Two different conversion methods were used for the forearm tilt angle to pitch frequency conversion: linear mapping method and F0 template-based method A perceptual evaluation has been performed with two well-trained normal speakers and ten subjects. The results of the evaluation study showed that both methods are able to produce better speech quality in terms of the naturalness.

  19. Continuum deformation of multi-agent systems

    CERN Document Server

    Rastgoftar, Hossein

    2016-01-01

    This monograph presents new algorithms for formation control of multi-agent systems (MAS) based on principles of continuum mechanics. Beginning with an overview of traditional methods, the author then introduces an innovative new approach whereby agents of an MAS are considered as particles in a continuum evolving in ℝn whose desired configuration is required to satisfy an admissible deformation function. The necessary theory and its validation on a mobile-agent-based swarm test bed are considered for two primary tasks: homogeneous transformation of the MAS and deployment of a random distribution of agents on a desired configuration. The framework for this model is based on homogeneous transformations for the evolution of an MAS under no inter-agent communication, local inter-agent communication, and intelligent perception by agents. Different communication protocols for MAS evolution, the robustness of tracking of a desired motion by an MAS evolving in ℝn, and the effect of communication delays in an MAS...

  20. Neuromuscular control of the point to point and oscillatory movements of a sagittal arm with the actor-critic reinforcement learning method.

    Science.gov (United States)

    Golkhou, Vahid; Parnianpour, Mohamad; Lucas, Caro

    2005-04-01

    In this study, we have used a single link system with a pair of muscles that are excited with alpha and gamma signals to achieve both point to point and oscillatory movements with variable amplitude and frequency.The system is highly nonlinear in all its physical and physiological attributes. The major physiological characteristics of this system are simultaneous activation of a pair of nonlinear muscle-like-actuators for control purposes, existence of nonlinear spindle-like sensors and Golgi tendon organ-like sensor, actions of gravity and external loading. Transmission delays are included in the afferent and efferent neural paths to account for a more accurate representation of the reflex loops.A reinforcement learning method with an actor-critic (AC) architecture instead of middle and low level of central nervous system (CNS), is used to track a desired trajectory. The actor in this structure is a two layer feedforward neural network and the critic is a model of the cerebellum. The critic is trained by state-action-reward-state-action (SARSA) method. The critic will train the actor by supervisory learning based on the prior experiences. Simulation studies of oscillatory movements based on the proposed algorithm demonstrate excellent tracking capability and after 280 epochs the RMS error for position and velocity profiles were 0.02, 0.04 rad and rad/s, respectively.