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.

A strategy learning model for autonomous agents based on classification

Directory of Open Access Journals (Sweden)

Śnieżyński Bartłomiej

2015-09-01

Full Text Available In this paper we propose a strategy learning model for autonomous agents based on classification. In the literature, the most commonly used learning method in agent-based systems is reinforcement learning. In our opinion, classification can be considered a good alternative. This type of supervised learning can be used to generate a classifier that allows the agent to choose an appropriate action for execution. Experimental results show that this model can be successfully applied for strategy generation even if rewards are delayed. We compare the efficiency of the proposed model and reinforcement learning using the farmer-pest domain and configurations of various complexity. In complex environments, supervised learning can improve the performance of agents much faster that reinforcement learning. If an appropriate knowledge representation is used, the learned knowledge may be analyzed by humans, which allows tracking the learning process

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.

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.

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'.

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...

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

"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.

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.

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

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

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

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.

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

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.

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.

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.

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.

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'

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.

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

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.

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.

'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.

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.

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.

Online Bahavior Aquisition of an Agent based on Coaching as Learning Assistance

Science.gov (United States)

Hirokawa, Masakazu; Suzuki, Kenji

This paper describes a novel methodology, namely ``Coaching'', which allows humans to give a subjective evaluation to an agent in an iterative manner. This is an interactive learning method to improve the reinforcement learning by modifying a reward function dynamically according to given evaluations by a trainer and the learning situation of the agent. We demonstrate that the agent can learn different reward functions by given instructions such as ``good or bad'' by human's observation, and can also obtain a set of behavior based on the learnt reward functions through several experiments.

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.

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

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.

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.

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

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.

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...

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.

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

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…

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

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.

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.

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.

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.

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...

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

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.

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).

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.

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

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.

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.

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.

An agent-based approach equipped with game theory. Strategic collaboration among learning agents during a dynamic market change in the California electricity crisis

Energy Technology Data Exchange (ETDEWEB)

Sueyoshi, Toshiyuki [Department of Management, New Mexico Institute of Mining and Technology, Socorro, NM 87801 (United States); Department of Industrial and Information Management, National Cheng Kung University, Tainan (China)

2010-09-15

An agent-based approach is a numerical (computer-intensive) method to explore the complex characteristics and dynamics of microeconomics. Using the agent-based approach, this study investigates the learning speed of traders and their strategic collaboration in a dynamic market change of electricity. An example of such a market change can be found in the California electricity crisis (2000-2001). This study incorporates the concept of partial reinforcement learning into trading agents and finds that they have two learning components: learning from a dynamic market change and learning from collaboration with other traders. The learning speed of traders becomes slow when a large fluctuation occurs in the power exchange market. The learning speed depends upon the type of traders, their learning capabilities and the fluctuation of market fundamentals. The degree of collaboration among traders gradually reduces during the electricity crisis. The strategic collaboration among traders is examined by a large simulator equipped with multiple learning capabilities. (author)

An agent-based approach equipped with game theory. Strategic collaboration among learning agents during a dynamic market change in the California electricity crisis

International Nuclear Information System (INIS)

Sueyoshi, Toshiyuki

2010-01-01

An agent-based approach is a numerical (computer-intensive) method to explore the complex characteristics and dynamics of microeconomics. Using the agent-based approach, this study investigates the learning speed of traders and their strategic collaboration in a dynamic market change of electricity. An example of such a market change can be found in the California electricity crisis (2000-2001). This study incorporates the concept of partial reinforcement learning into trading agents and finds that they have two learning components: learning from a dynamic market change and learning from collaboration with other traders. The learning speed of traders becomes slow when a large fluctuation occurs in the power exchange market. The learning speed depends upon the type of traders, their learning capabilities and the fluctuation of market fundamentals. The degree of collaboration among traders gradually reduces during the electricity crisis. The strategic collaboration among traders is examined by a large simulator equipped with multiple learning capabilities. (author)

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 .

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...

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.

An intelligent agent for optimal river-reservoir system management

Science.gov (United States)

Rieker, Jeffrey D.; Labadie, John W.

2012-09-01

A generalized software package is presented for developing an intelligent agent for stochastic optimization of complex river-reservoir system management and operations. Reinforcement learning is an approach to artificial intelligence for developing a decision-making agent that learns the best operational policies without the need for explicit probabilistic models of hydrologic system behavior. The agent learns these strategies experientially in a Markov decision process through observational interaction with the environment and simulation of the river-reservoir system using well-calibrated models. The graphical user interface for the reinforcement learning process controller includes numerous learning method options and dynamic displays for visualizing the adaptive behavior of the agent. As a case study, the generalized reinforcement learning software is applied to developing an intelligent agent for optimal management of water stored in the Truckee river-reservoir system of California and Nevada for the purpose of streamflow augmentation for water quality enhancement. The intelligent agent successfully learns long-term reservoir operational policies that specifically focus on mitigating water temperature extremes during persistent drought periods that jeopardize the survival of threatened and endangered fish species.

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.

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.

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…

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

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

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.

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.

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.

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...

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.

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.

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.

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.

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.

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.

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...

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.

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.

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.

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

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.

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

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.

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.

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

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.

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)

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

Conversational Agents in E-Learning

Science.gov (United States)

Kerry, Alice; Ellis, Richard; Bull, Susan

This paper discusses the use of natural language or 'conversational' agents in e-learning environments. We describe and contrast the various applications of conversational agent technology represented in the e-learning literature, including tutors, learning companions, language practice and systems to encourage reflection. We offer two more detailed examples of conversational agents, one which provides learning support, and the other support for self-assessment. Issues and challenges for developers of conversational agent systems for e-learning are identified and discussed.

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

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.

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,

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.

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...

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.

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.

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...

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.

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

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.

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...

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.

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.

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,

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...

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.

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.

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.

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

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.

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.

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

Learning-based diagnosis and repair

NARCIS (Netherlands)

Roos, Nico

2017-01-01

This paper proposes a new form of diagnosis and repair based on reinforcement learning. Self-interested agents learn locally which agents may provide a low quality of service for a task. The correctness of learned assessments of other agents is proved under conditions on exploration versus

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

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.

E-Learning Agents

Science.gov (United States)

Gregg, Dawn G.

2007-01-01

Purpose: The purpose of this paper is to illustrate the advantages of using intelligent agents to facilitate the location and customization of appropriate e-learning resources and to foster collaboration in e-learning environments. Design/methodology/approach: This paper proposes an e-learning environment that can be used to provide customized…

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.

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

The role of family planning communications--an agent of reinforcement or change.

Science.gov (United States)

Chen, E C

1981-12-01

Results are presented of a multiple classification analysis of responses to a 1972 KAP survey in Taiwan of 2013 married women aged 18-34 designed to determine whether family planning communication is primarily a reinforcement agent or a change agent. 2 types of independent variables, social demographic variables including age, number of children, residence, education, employment status, and duration of marriage; and social climate variables including ever receiving family planning information from mass media and ever discussing family planning with others, were used. KAP levels, the dependent variables, were measured by 2 variables each: awareness of effective methods and awareness of government supply of contraceptives for knowledge, wish for additional children and approve of 2-child family for attitude, and never use contraception and neither want children nor use contraception for practice. Social demographic and attitudinal variables were found to be the critical ones, while social climate and knowledge variables had only negligible effects on various stages of family planning adoption, indicating that family planning communications functioned primarily as a reinforcement agent. The effects of social demographic variables were prominent in all stages of contraceptive adoption. Examination of effects of individual variables on various stages of family planning adoption still supported the argument that family planning communications played a reinforcement role. Family planning communications functioned well in diffusing family planning knowledge and accessibility, but social demographic variables and desire for additional children were the most decisive influences on use of contraception.

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.

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.

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.

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...

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

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.

Agents in E-learning

Directory of Open Access Journals (Sweden)

S. Mencke

2007-12-01

Full Text Available This paper presents a framework to describe thecrossover domain of e-learning and agent technology.Furthermore it is used to classify existing work and possiblestarting points for the future development of agenttechniques and technologies order to enhance theperformance and the effectiveness of several aspects of elearningsystems. Agents are not a new concept but their usein the field of e-learning constitutes a basis for consequentialadvances.

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 ...

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.

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.

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…

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.

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.

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.

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.

Homeostatic Agent for General Environment

Science.gov (United States)

Yoshida, Naoto

2018-03-01

One of the essential aspect in biological agents is dynamic stability. This aspect, called homeostasis, is widely discussed in ethology, neuroscience and during the early stages of artificial intelligence. Ashby's homeostats are general-purpose learning machines for stabilizing essential variables of the agent in the face of general environments. However, despite their generality, the original homeostats couldn't be scaled because they searched their parameters randomly. In this paper, first we re-define the objective of homeostats as the maximization of a multi-step survival probability from the view point of sequential decision theory and probabilistic theory. Then we show that this optimization problem can be treated by using reinforcement learning algorithms with special agent architectures and theoretically-derived intrinsic reward functions. Finally we empirically demonstrate that agents with our architecture automatically learn to survive in a given environment, including environments with visual stimuli. Our survival agents can learn to eat food, avoid poison and stabilize essential variables through theoretically-derived single intrinsic reward formulations.

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

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

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

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.

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.

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

Quantum Speedup for Active Learning Agents

Directory of Open Access Journals (Sweden)

Giuseppe Davide Paparo

2014-07-01

Full Text Available Can quantum mechanics help us build intelligent learning agents? A defining signature of intelligent behavior is the capacity to learn from experience. However, a major bottleneck for agents to learn in real-life situations is the size and complexity of the corresponding task environment. Even in a moderately realistic environment, it may simply take too long to rationally respond to a given situation. If the environment is impatient, allowing only a certain time for a response, an agent may then be unable to cope with the situation and to learn at all. Here, we show that quantum physics can help and provide a quadratic speedup for active learning as a genuine problem of artificial intelligence. This result will be particularly relevant for applications involving complex task environments.

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.

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.

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...

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.

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

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.

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.

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.

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

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

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.

Investigation Characteristics Of Pulp Fibers AS Green Potential Polymer Reinforcing Agents

OpenAIRE

Masruchin, Nanang; Subyakto

2012-01-01

Three kinds of pulp fiber (i.e. kenaf, pineapple and coconut fiber)were characterized as reinforcing agents in compositematerials to be applied at automotive interior industry.Abetter understanding on characteristics of fiber will lead to enhance interface adhesion between fiber and matrices. Furthermore, it will improve the properties of polymer significantly. Chemical, surface compositions as well as morphology of pulp fiber were investigated using TAPPI standard test method, Fourier Transf...

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...

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

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.

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....

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.

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 ...

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.

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.

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.

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.

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...

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…

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.

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

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.

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...

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...

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...

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.

Personalized E- learning System Based on Intelligent Agent

Science.gov (United States)

Duo, Sun; Ying, Zhou Cai

Lack of personalized learning is the key shortcoming of traditional e-Learning system. This paper analyzes the personal characters in e-Learning activity. In order to meet the personalized e-learning, a personalized e-learning system based on intelligent agent was proposed and realized in the paper. The structure of system, work process, the design of intelligent agent and the realization of intelligent agent were introduced in the paper. After the test use of the system by certain network school, we found that the system could improve the learner's initiative participation, which can provide learners with personalized knowledge service. Thus, we thought it might be a practical solution to realize self- learning and self-promotion in the lifelong education age.

Preparing Students for Future Learning with Teachable Agents

Science.gov (United States)

Chin, Doris B.; Dohmen, Ilsa M.; Cheng, Britte H.; Oppezzo, Marily A.; Chase, Catherine C.; Schwartz, Daniel L.

2010-01-01

One valuable goal of instructional technologies in K-12 education is to prepare students for future learning. Two classroom studies examined whether Teachable Agents (TA) achieves this goal. TA is an instructional technology that draws on the social metaphor of teaching a computer agent to help students learn. Students teach their agent by…

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.

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...

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.

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...

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

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…

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

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.

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

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.

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

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.

E-learning paradigms and applications agent-based approach

CERN Document Server

Jain, Lakhmi

2014-01-01

Teaching and learning paradigms have attracted increased attention especially in the last decade. Immense developments of different ICT technologies and services have paved the way for alternative but effective approaches in educational processes. Many concepts of the agent technology, such as intelligence, autonomy, and cooperation, have had a direct positive impact on many of the requests imposed on modern e-learning systems and educational processes. This book presents the state-of-the-art of e-learning and tutoring systems, and discusses their capabilities and benefits that stem from integrating software agents. We hope that the presented work will be of a great use to our colleagues and researchers interested in the e-learning and agent technology.    

Impacts of Pedagogical Agent Gender in an Accessible Learning Environment

Science.gov (United States)

Schroeder, Noah L.; Adesope, Olusola O.

2015-01-01

Advances in information technologies have resulted in the use of pedagogical agents to facilitate learning. Although several studies have been conducted to examine the effects of pedagogical agents on learning, little is known about gender stereotypes of agents and how those stereotypes influence student learning and attitudes. This study…

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.

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

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...

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.

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.

Unicorn: Continual Learning with a Universal, Off-policy Agent

OpenAIRE

Mankowitz, Daniel J.; Žídek, Augustin; Barreto, André; Horgan, Dan; Hessel, Matteo; Quan, John; Oh, Junhyuk; van Hasselt, Hado; Silver, David; Schaul, Tom

2018-01-01

Some real-world domains are best characterized as a single task, but for others this perspective is limiting. Instead, some tasks continually grow in complexity, in tandem with the agent's competence. In continual learning, also referred to as lifelong learning, there are no explicit task boundaries or curricula. As learning agents have become more powerful, continual learning remains one of the frontiers that has resisted quick progress. To test continual learning capabilities we consider a ...

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

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.

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.

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.

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.

Deep imitation learning for 3D navigation tasks.

Science.gov (United States)

Hussein, Ahmed; Elyan, Eyad; Gaber, Mohamed Medhat; Jayne, Chrisina

2018-01-01

Deep learning techniques have shown success in learning from raw high-dimensional data in various applications. While deep reinforcement learning is recently gaining popularity as a method to train intelligent agents, utilizing deep learning in imitation learning has been scarcely explored. Imitation learning can be an efficient method to teach intelligent agents by providing a set of demonstrations to learn from. However, generalizing to situations that are not represented in the demonstrations can be challenging, especially in 3D environments. In this paper, we propose a deep imitation learning method to learn navigation tasks from demonstrations in a 3D environment. The supervised policy is refined using active learning in order to generalize to unseen situations. This approach is compared to two popular deep reinforcement learning techniques: deep-Q-networks and Asynchronous actor-critic (A3C). The proposed method as well as the reinforcement learning methods employ deep convolutional neural networks and learn directly from raw visual input. Methods for combining learning from demonstrations and experience are also investigated. This combination aims to join the generalization ability of learning by experience with the efficiency of learning by imitation. The proposed methods are evaluated on 4 navigation tasks in a 3D simulated environment. Navigation tasks are a typical problem that is relevant to many real applications. They pose the challenge of requiring demonstrations of long trajectories to reach the target and only providing delayed rewards (usually terminal) to the agent. The experiments show that the proposed method can successfully learn navigation tasks from raw visual input while learning from experience methods fail to learn an effective policy. Moreover, it is shown that active learning can significantly improve the performance of the initially learned policy using a small number of active samples.

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…

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.

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.

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.

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

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...

Agent-specific learning signals for self-other distinction during mentalising.

Directory of Open Access Journals (Sweden)

Sam Ereira

2018-04-01

Full Text Available Humans have a remarkable ability to simulate the minds of others. How the brain distinguishes between mental states attributed to self and mental states attributed to someone else is unknown. Here, we investigated how fundamental neural learning signals are selectively attributed to different agents. Specifically, we asked whether learning signals are encoded in agent-specific neural patterns or whether a self-other distinction depends on encoding agent identity separately from this learning signal. To examine this, we tasked subjects to learn continuously 2 models of the same environment, such that one was selectively attributed to self and the other was selectively attributed to another agent. Combining computational modelling with magnetoencephalography (MEG enabled us to track neural representations of prediction errors (PEs and beliefs attributed to self, and of simulated PEs and beliefs attributed to another agent. We found that the representational pattern of a PE reliably predicts the identity of the agent to whom the signal is attributed, consistent with a neural self-other distinction implemented via agent-specific learning signals. Strikingly, subjects exhibiting a weaker neural self-other distinction also had a reduced behavioural capacity for self-other distinction and displayed more marked subclinical psychopathological traits. The neural self-other distinction was also modulated by social context, evidenced in a significantly reduced decoding of agent identity in a nonsocial control task. Thus, we show that self-other distinction is realised through an encoding of agent identity intrinsic to fundamental learning signals. The observation that the fidelity of this encoding predicts psychopathological traits is of interest as a potential neurocomputational psychiatric biomarker.

Feature selection for domain knowledge representation through multitask learning

CSIR Research Space (South Africa)

Rosman, Benjamin S

2014-10-01

Full Text Available represent stimuli of interest, and rich feature sets which increase the dimensionality of the space and thus the difficulty of the learning problem. We focus on a multitask reinforcement learning setting, where the agent is learning domain knowledge...

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).

Use of frontal lobe hemodynamics as reinforcement signals to an adaptive controller.

Directory of Open Access Journals (Sweden)

Marcello M DiStasio

Full Text Available Decision-making ability in the frontal lobe (among other brain structures relies on the assignment of value to states of the animal and its environment. Then higher valued states can be pursued and lower (or negative valued states avoided. The same principle forms the basis for computational reinforcement learning controllers, which have been fruitfully applied both as models of value estimation in the brain, and as artificial controllers in their own right. This work shows how state desirability signals decoded from frontal lobe hemodynamics, as measured with near-infrared spectroscopy (NIRS, can be applied as reinforcers to an adaptable artificial learning agent in order to guide its acquisition of skills. A set of experiments carried out on an alert macaque demonstrate that both oxy- and deoxyhemoglobin concentrations in the frontal lobe show differences in response to both primarily and secondarily desirable (versus undesirable stimuli. This difference allows a NIRS signal classifier to serve successfully as a reinforcer for an adaptive controller performing a virtual tool-retrieval task. The agent's adaptability allows its performance to exceed the limits of the NIRS classifier decoding accuracy. We also show that decoding state desirabilities is more accurate when using relative concentrations of both oxyhemoglobin and deoxyhemoglobin, rather than either species alone.

Enhancing E-Learning through Web Service and Intelligent Agents

Directory of Open Access Journals (Sweden)

Nasir Hussain

2006-04-01

Full Text Available E-learning is basically the integration of various technologies. E-Learning technology is now maturing and we can find a multiplicity of standards. New technologies such as agents and web services are promising better results. In this paper we have proposed an e-learning architecture that is dependent on intelligent agent systems and web services. These communication technologies will make the architecture more robust, scalable and efficient.

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

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.

What Learning Systems do Intelligent Agents Need? Complementary Learning Systems Theory Updated.

Science.gov (United States)

Kumaran, Dharshan; Hassabis, Demis; McClelland, James L

2016-07-01

We update complementary learning systems (CLS) theory, which holds that intelligent agents must possess two learning systems, instantiated in mammalians in neocortex and hippocampus. The first gradually acquires structured knowledge representations while the second quickly learns the specifics of individual experiences. We broaden the role of replay of hippocampal memories in the theory, noting that replay allows goal-dependent weighting of experience statistics. We also address recent challenges to the theory and extend it by showing that recurrent activation of hippocampal traces can support some forms of generalization and that neocortical learning can be rapid for information that is consistent with known structure. Finally, we note the relevance of the theory to the design of artificial intelligent agents, highlighting connections between neuroscience and machine learning. Copyright © 2016 Elsevier Ltd. All rights reserved.

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.

[Effect of amount of silane coupling agent on flexural strength of dental composite resins reinforced with aluminium borate whisker].

Science.gov (United States)

Zhu, Ming-yi; Zhang, Xiu-yin

2015-06-01

To evaluate the effect of amount of silane coupling agent on flexural strength of dental composite resins reinforced with aluminium borate whisker (ABW). ABW was surface-treated with 0%, 1%, 2%, 3% and 4% silan coupling agent (γ-MPS), and mixed with resin matrix to synthesize 5 groups of composite resins. After heat-cured at 120 degrees centigrade for 1 h, specimens were tested in three-point flexure to measure strength according to ISO-4049. One specimen was selected randomly from each group and observed under scanning electron microscope (SEM). The data was analyzed with SAS 9.2 software package. The flexural strength (117.93±11.9 Mpa) of the group treated with 2% silane coupling agent was the highest, and significantly different from that of the other 4 groups (α=0.01). The amount of silane coupling agent has impact on the flexural strength of dental composite resins reinforced with whiskers; The flexual strength will be reduced whenever the amount is higher or lower than the threshold. Supported by Research Fund of Science and Technology Committee of Shanghai Municipality (08DZ2271100).

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....

The dispersion of SWCNTs treated by coupling and dispersing agents in fiber reinforced polymer composities

Science.gov (United States)

Duan, Yuexin; Yuan, Lu; Zhao, Yan; Guan, Fengxia

2007-07-01

It is an obstacle issue for Carbon nanotubes (CNTs) applied in fiber reinforced polymer composites that CNTs is dispersed in nano-level, particularly for single-wall Carbon nanotubes (SWCNTs). In this paper, SWCNTs were treated by the coupling agent like volan and dispersing agent as BYK to improve the dispersion in the Glass Fiber/Epoxy composites. The result of dispersion of SWCNTs in composites was observed by Scanning electron microscopy (SEM). Then the Glass Transition Temperature (Tg) of these kinds of composites with treated and untreated SWCNTs were obtained by Dynamic Mechanical Thermal Analysis (DMTA). Moreover, the bending properties of these composites were tested.

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...

Nash Equilibrium of Social-Learning Agents in a Restless Multiarmed Bandit Game.

Science.gov (United States)

Nakayama, Kazuaki; Hisakado, Masato; Mori, Shintaro

2017-05-16

We study a simple model for social-learning agents in a restless multiarmed bandit (rMAB). The bandit has one good arm that changes to a bad one with a certain probability. Each agent stochastically selects one of the two methods, random search (individual learning) or copying information from other agents (social learning), using which he/she seeks the good arm. Fitness of an agent is the probability to know the good arm in the steady state of the agent system. In this model, we explicitly construct the unique Nash equilibrium state and show that the corresponding strategy for each agent is an evolutionarily stable strategy (ESS) in the sense of Thomas. It is shown that the fitness of an agent with ESS is superior to that of an asocial learner when the success probability of social learning is greater than a threshold determined from the probability of success of individual learning, the probability of change of state of the rMAB, and the number of agents. The ESS Nash equilibrium is a solution to Rogers' paradox.

Active Learning for Autonomous Intelligent Agents: Exploration, Curiosity, and Interaction

OpenAIRE

Lopes, Manuel; Montesano, Luis

2014-01-01

In this survey we present different approaches that allow an intelligent agent to explore autonomous its environment to gather information and learn multiple tasks. Different communities proposed different solutions, that are in many cases, similar and/or complementary. These solutions include active learning, exploration/exploitation, online-learning and social learning. The common aspect of all these approaches is that it is the agent to selects and decides what information to gather next. ...

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

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

Pedagogical Agents as Learning Companions: The Impact of Agent Emotion and Gender

Science.gov (United States)

Kim, Yanghee; Baylor, A. L.; Shen, E.

2007-01-01

The potential of emotional interaction between human and computer has recently interested researchers in human-computer interaction. The instructional impact of this interaction in learning environments has not been established, however. This study examined the impact of emotion and gender of a pedagogical agent as a learning companion (PAL) on…

An Empirical Study of AI Population Dynamics with Million-agent Reinforcement Learning

OpenAIRE

Yang, Yaodong; Yu, Lantao; Bai, Yiwei; Wang, Jun; Zhang, Weinan; Wen, Ying; Yu, Yong

2017-01-01

In this paper, we conduct an empirical study on discovering the ordered collective dynamics obtained by a population of artificial intelligence (AI) agents. Our intention is to put AI agents into a simulated natural context, and then to understand their induced dynamics at the population level. In particular, we aim to verify if the principles developed in the real world could also be used in understanding an artificially-created intelligent population. To achieve this, we simulate a large-sc...

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.

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

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.

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)

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....

Construction of a Learning Agent Handling Its Rewards According to Environmental Situations

Science.gov (United States)

Moriyama, Koichi; Numao, Masayuki

The authors aim at constructing an agent which learns appropriate actions in a Multi-Agent environment with and without social dilemmas. For this aim, the agent must have nonrationality that makes it give up its own profit when it should do that. Since there are many studies on rational learning that brings more and more profit, it is desirable to utilize them for constructing the agent. Therefore, we use a reward-handling manner that makes internal evaluation from the agent's rewards, and then the agent learns actions by a rational learning method with the internal evaluation. If the agent has only a fixed manner, however, it does not act well in the environment with and without dilemmas. Thus, the authors equip the agent with several reward-handling manners and criteria for selecting an effective one for the environmental situation. In the case of humans, what generates the internal evaluation is usually called emotion. Hence, this study also aims at throwing light on emotional activities of humans from a constructive view. In this paper, we divide a Multi-Agent environment into three situations and construct an agent having the reward-handling manners and the criteria. We observe that the agent acts well in all the three Multi-Agent situations composed of homogeneous agents.

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.

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.

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.

Courseware Development with Animated Pedagogical Agents in Learning System to Improve Learning Motivation

Science.gov (United States)

Chin, Kai-Yi; Hong, Zeng-Wei; Huang, Yueh-Min; Shen, Wei-Wei; Lin, Jim-Min

2016-01-01

The addition of animated pedagogical agents (APAs) in computer-assisted learning (CAL) systems could successfully enhance students' learning motivation and engagement in learning activities. Conventionally, the APA incorporated multimedia materials are constructed through the cooperation of teachers and software programmers. However, the thinking…

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

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

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.

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.

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...

Balancing Two-Player Stochastic Games with Soft Q-Learning

OpenAIRE

Grau-Moya, Jordi; Leibfried, Felix; Bou-Ammar, Haitham

2018-01-01

Within the context of video games the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision makers. Current frameworks for stochastic games and reinforcement learning prohibit tuneable strategies as they seek optimal performance. In this paper, we enable such tuneable behaviour by generalising soft Q-learning to stochastic games, where more than one agent interact strategically. We contribute both theoretic...

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.

Incremental learning of skill collections based on intrinsic motivation

Science.gov (United States)

Metzen, Jan H.; Kirchner, Frank

2013-01-01

Life-long learning of reusable, versatile skills is a key prerequisite for embodied agents that act in a complex, dynamic environment and are faced with different tasks over their lifetime. We address the question of how an agent can learn useful skills efficiently during a developmental period, i.e., when no task is imposed on him and no external reward signal is provided. Learning of skills in a developmental period needs to be incremental and self-motivated. We propose a new incremental, task-independent skill discovery approach that is suited for continuous domains. Furthermore, the agent learns specific skills based on intrinsic motivation mechanisms that determine on which skills learning is focused at a given point in time. We evaluate the approach in a reinforcement learning setup in two continuous domains with complex dynamics. We show that an intrinsically motivated, skill learning agent outperforms an agent which learns task solutions from scratch. Furthermore, we compare different intrinsic motivation mechanisms and how efficiently they make use of the agent's developmental period. PMID:23898265

Learning Networks: connecting people, organizations, autonomous agents and learning resources to establish the emergence of effective lifelong learning

NARCIS (Netherlands)

Koper, Rob; Sloep, Peter

2003-01-01

Koper, E.J.R., Sloep, P.B. (2002) Learning Networks connecting people, organizations, autonomous agents and learning resources to establish the emergence of effective lifelong learning. RTD Programma into Learning Technologies 2003-2008. More is different… Heerlen, Nederland: Open Universiteit

An Active Learning Exercise for Introducing Agent-Based Modeling

Science.gov (United States)

Pinder, Jonathan P.

2013-01-01

Recent developments in agent-based modeling as a method of systems analysis and optimization indicate that students in business analytics need an introduction to the terminology, concepts, and framework of agent-based modeling. This article presents an active learning exercise for MBA students in business analytics that demonstrates agent-based…

Learning automaton newtork and its dynamics. Gakushu automaton network to sono dynamics

Energy Technology Data Exchange (ETDEWEB)

Quan, F [Hiroshima-Denki Institute of Technology, Hiroshima (Jpaan); Unno, F; Hirata, H [Chiba Univ., Chiba (Japan)

1991-10-20

In order to construct a distributed processing system having learning automata as autonomous elements, a reinforcement learning network of the automaton is proposed and it{prime}s dynamics is investigated. In this paper, it is attempted to add another level of meaning to computational cooperativity by using a reinforcement learning network with generalized leaning automata. The collection of learning automata in the team situation acts as self-interested agents that work toward improving their performance with respect to their individual preference ordering. In the global state space of the network, the case of partially synchronous stochastic process is considered. In this case, the existence of mean field is shown and a reinforcement learning algorithm which can make the dynamics on the average reinforcement trajectory is presented. This algorithm is shown to have a high convergence speed as a result of a simple experiment. 14 refs., 9 figs.

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

Incremental Learning of Skill Collections based on Intrinsic Motivation

Directory of Open Access Journals (Sweden)

Jan Hendrik Metzen

2013-07-01

Full Text Available Life-long learning of reusable, versatile skills is a key prerequisite forembodied agents that act in a complex, dynamic environment and are faced withdifferent tasks over their lifetime. We address the question of how an agentcan learn useful skills efficiently during a developmental period,i.e., when no task is imposed on him and no external reward signal is provided.Learning of skills in a developmental period needs to be incremental andself-motivated. We propose a new incremental, task-independent skill discoveryapproach that is suited for continuous domains. Furthermore, the agent learnsspecific skills based on intrinsic motivation mechanisms thatdetermine on which skills learning is focused at a given point in time. Weevaluate the approach in a reinforcement learning setup in two continuousdomains with complex dynamics. We show that an intrinsically motivated, skilllearning agent outperforms an agent which learns task solutions from scratch.Furthermore, we compare different intrinsic motivation mechanisms and howefficiently they make use of the agent's developmental period.

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

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

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.

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

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.

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.

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.

An embodiment effect in computer-based learning with animated pedagogical agents.

Science.gov (United States)

Mayer, Richard E; DaPra, C Scott

2012-09-01

How do social cues such as gesturing, facial expression, eye gaze, and human-like movement affect multimedia learning with onscreen agents? To help address this question, students were asked to twice view a 4-min narrated presentation on how solar cells work in which the screen showed an animated pedagogical agent standing to the left of 11 successive slides. Across three experiments, learners performed better on a transfer test when a human-voiced agent displayed human-like gestures, facial expression, eye gaze, and body movement than when the agent did not, yielding an embodiment effect. In Experiment 2 the embodiment effect was found when the agent spoke in a human voice but not in a machine voice. In Experiment 3, the embodiment effect was found both when students were told the onscreen agent was consistent with their choice of agent characteristics and when inconsistent. Students who viewed a highly embodied agent also rated the social attributes of the agent more positively than did students who viewed a nongesturing agent. The results are explained by social agency theory, in which social cues in a multimedia message prime a feeling of social partnership in the learner, which leads to deeper cognitive processing during learning, and results in a more meaningful learning outcome as reflected in transfer test performance.

Pedagogical Agents as Learning Companions: The Role of Agent Competency and Type of Interaction

Science.gov (United States)

Kim, Yanghee; Baylor, Amy L.

2006-01-01

This study was designed to examine the effects of the competency (low vs. high) and interaction type (proactive vs. responsive) of pedagogical agents as learning companions (PALs) on learning, self-efficacy, and attitudes. Participants were 72 undergraduates in an introductory computer-literacy course who were randomly assigned to one of four…

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

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...

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.

Enhancement of interfacial properties of basalt fiber reinforced nylon 6 matrix composites with silane coupling agents

Directory of Open Access Journals (Sweden)

2010-10-01

Full Text Available In this work solution surface treatment was applied for producing basalt fiber reinforced PA6 matrix composites. Beyond scanning electron microscopy, static and dynamic mechanical tests, dynamic mechanical analysis of composites was used for qualifying the interfacial adhesion in a wide temperature range. The loss factor peak height of loss factor is particularly important, because it is in close relationship with the mobility of polymer molecular chain segments and side groups, hence it correlates with the number and strength of primary or secondary bondings established between the matrix and the basalt fibers. It was proven, that the interfacial adhesion between basalt fibers and polyamide can be largely improved by the application of silane coupling agents in the entire usage temperature range of composites. The presence of coupling agents on the surface of basalt fibers was proven by Fourier transform infrared spectroscopy. The best results were obtained by 3-glycidoxypropyltrimethoxysilane coupling agent.

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.

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.

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.

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.

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.

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.

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.

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.

Coordinating Decentralized Learning and Conflict Resolution across Agent Boundaries

Science.gov (United States)

Cheng, Shanjun

2012-01-01

It is crucial for embedded systems to adapt to the dynamics of open environments. This adaptation process becomes especially challenging in the context of multiagent systems because of scalability, partial information accessibility and complex interaction of agents. It is a challenge for agents to learn good policies, when they need to plan and…

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.

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.

Evolutionary and adaptive learning in complex markets: a brief summary

Science.gov (United States)

Hommes, Cars H.

2007-06-01

We briefly review some work on expectations and learning in complex markets, using the familiar demand-supply cobweb model. We discuss and combine two different approaches on learning. According to the adaptive learning approach, agents behave as econometricians using time series observations to form expectations, and update the parameters as more observations become available. This approach has become popular in macro. The second approach has an evolutionary flavor and is sometimes referred to as reinforcement learning. Agents employ different forecasting strategies and evaluate these strategies based upon a fitness measure, e.g. past realized profits. In this framework, boundedly rational agents switch between different, but fixed behavioral rules. This approach has become popular in finance. We combine evolutionary and adaptive learning to model complex markets and discuss whether this theory can match empirical facts and forecasting behavior in laboratory experiments with human subjects.

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.

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...

Thermomechanical analyses of phenolic foam reinforced with glass fiber mat

International Nuclear Information System (INIS)

Zhou, Jintang; Yao, Zhengjun; Chen, Yongxin; Wei, Dongbo; Wu, Yibing

2013-01-01

Highlights: • Over 10% glass fiber was used to reinforce phenolic foam in the shape of glass fiber mat. • Nucleating agents were used together with glass fiber mat and improved tensile strength of phenolic foam by 215.6%. • Nucleating agents lead to a smaller bubble size of phenolic foam. • The glass transition temperature of phenolic foam remained unchanged during the reinforcement. - Abstract: In this paper, thermomechanical analysis (TMA) and dynamic mechanical analysis were employed to study the properties of phenolic foam reinforced with glass fiber mat. Unreinforced phenolic foam was taken as the control sample. Mechanical tests and scanning electron microscopy were performed to confirm the results of TMA. The results show that glass fiber mat reinforcement improves the mechanical performance of phenolic foam, and nucleating agents improve it further. Phenolic foam reinforced with glass fiber mat has a smaller thermal expansion coefficient compared with unreinforced foam. The storage modulus of the reinforced phenolic foam is also higher than that in unreinforced foam, whereas the loss modulus of the former is lower than that of the latter. The glass transition temperature of the phenolic foam matrix remains unchanged during the reinforcement

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.

Global reinforcement training of CrossNets

Science.gov (United States)

Ma, Xiaolong

2007-10-01

Hybrid "CMOL" integrated circuits, incorporating advanced CMOS devices for neural cell bodies, nanowires as axons and dendrites, and latching switches as synapses, may be used for the hardware implementation of extremely dense (107 cells and 1012 synapses per cm2) neuromorphic networks, operating up to 10 6 times faster than their biological prototypes. We are exploring several "Cross- Net" architectures that accommodate the limitations imposed by CMOL hardware and should allow effective training of the networks without a direct external access to individual synapses. Our studies have show that CrossNets based on simple (two-terminal) crosspoint devices can work well in at least two modes: as Hop-field networks for associative memory and multilayer perceptrons for classification tasks. For more intelligent tasks (such as robot motion control or complex games), which do not have "examples" for supervised learning, more advanced training methods such as the global reinforcement learning are necessary. For application of global reinforcement training algorithms to CrossNets, we have extended Williams's REINFORCE learning principle to a more general framework and derived several learning rules that are more suitable for CrossNet hardware implementation. The results of numerical experiments have shown that these new learning rules can work well for both classification tasks and reinforcement tasks such as the cartpole balancing control problem. Some limitations imposed by the CMOL hardware need to be carefully addressed for the the successful application of in situ reinforcement training to CrossNets.

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.

Pedagogical Agents as Learning Companions: The Role of Agent Competency and Type of Interaction

OpenAIRE

Kim, Yanghee; Baylor, Amy L.; PALS Group,

2006-01-01

This study was designed to examine the effects of the competency (low vs. high) and interaction type (proactive vs. responsive) of pedagogical agents as learning companions (PALs) on learning, self-efficacy, and attitudes. Participants were 72 undergraduates in an introductory computer-literacy course who were randomly assigned to one of four treatments: Low-Proactive, Low-Responsive, High-Proactive, and High-Responsive. Results indicated a main effect for PAL competency. Students who worked ...

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

Which is the best intrinsic motivation signal for learning multiple skills?

Directory of Open Access Journals (Sweden)

Vieri Giuliano Santucci

2013-11-01

Full Text Available Humans and other biological agents are able to autonomously learn and cache different skills in the absence of any biological pressure or any assigned task. In this respect, Intrinsic Motivations (i.e. motivations not connected to reward-related stimuli play a cardinal role in animal learning, and can be considered as a fundamental tool for developing more autonomous and more adaptive artificial agents. In this work, we provide an exhaustive analysis of a scarcely investigated problem: which kind of IM reinforcement signal is the most suitable for driving the acquisition of multiple skills in the shortest time? To this purpose we implemented an artificial agent with a hierarchical architecture that allows to learn and cache different skills. We tested the system in a setup with continuous states and actions, in particular, with a cinematic robotic arm that has to learn different reaching tasks. We compare the results of different versions of the system driven by several different intrinsic motivation signals. The results show a that intrinsic reinforcements purely based on the knowledge of the system are not appropriate to guide the acquisition of multiple skills, and b that the stronger the link between the IM signal and the competence of the system, the better the performance.

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.

Evaluating Persuasion Strategies and Deep Reinforcement Learning methods for Negotiation Dialogue agents

OpenAIRE

Keizer, Simon; Guhe, Markus; Cuayáhuitl, Heriberto; Efstathiou, Ioannis; Engelbrecht, Klaus-Peter; Dobre, Mihai; Lascarides, Alexandra; Lemon, Oliver

2017-01-01

In this paper we present a comparative evaluation of various negotiation strategies within an online version of the game “Settlers of Catan”. The comparison is based on human subjects playing games against artificial game-playing agents (‘bots’) which implement different negotiation dialogue strategies, using a chat dialogue interface to negotiate trades. Our results suggest that a negotiation strategy that uses persuasion, as well as a strategy that is trained from data using Deep Reinforcem...

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.

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.

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.

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.

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

Situation Creator: A Pedagogical Agent Creating Learning Opportunities

NARCIS (Netherlands)

Miao, Yongwu; Hoppe, Ulrich; Pinkwart, Niels

2007-01-01

Miao, Y., Hoppe, H. U., & Pinkwart, N. (2007). Situation Creator: A Pedagogical Agent Creating Learning Opportunities. In R. Luckin, K. Koedinger & J. Greer (Eds.), Proceedings of the 13th International Conference on Artificial Intelligence in Education (pp. 614-617). Amsterdam, The Netherlands: IOS

Analysis of Foreign Exchange Interventions by Intervention Agent with an Artificial Market Approach

Science.gov (United States)

Matsui, Hiroki; Tojo, Satoshi

We propose a multi-agent system which learns intervention policies and evaluates the effect of interventions in an artificial foreign exchange market. Izumi et al. had presented a system called AGEDASI TOF to simulate artificial market, together with a support system for the government to decide foreign exchange policies. However, the system needed to fix the amount of governmental intervention prior to the simulation, and was not realistic. In addition, the interventions in the system did not affect supply and demand of currencies; thus we could not discuss the effect of intervention correctly. First, we improve the system so as to make much of the weights of influential factors. Thereafter, we introduce an intervention agent that has the role of the central bank to stabilize the market. We could show that the agent learned the effective intervention policies through the reinforcement learning, and that the exchange rate converged to a certain extent in the expected range. We could also estimate the amount of intervention, showing the efficacy of signaling. In this model, in order to investigate the aliasing of the perception of the intervention agent, we introduced a pseudo-agent who was supposed to be able to observe all the behaviors of dealer agents; with this super-agent, we discussed the adequate granularity for a market state description.

Improved monolithic reinforced concrete construction for nuclear power stations

International Nuclear Information System (INIS)

Guenther, P.; Fischer, K.

1983-01-01

Experience has shown that in applying monolithic reinforced concrete in nuclear power plant construction the following auxiliary means are useful: measuring sheets in assembling, welding gauges for reaching high tolerance accuracies of prefabricated reinforced concrete members, suitable lining materials, formwork anchorage and formwork release agents, concrete workability agents, mechanized procedures for finishing and assembling. These means were successfully tested in constructing the Greifswald nuclear power station

Quantum-enhanced deliberation of learning agents using trapped ions

Science.gov (United States)

Dunjko, V.; Friis, N.; Briegel, H. J.

2015-02-01

A scheme that successfully employs quantum mechanics in the design of autonomous learning agents has recently been reported in the context of the projective simulation (PS) model for artificial intelligence. In that approach, the key feature of a PS agent, a specific type of memory which is explored via random walks, was shown to be amenable to quantization, allowing for a speed-up. In this work we propose an implementation of such classical and quantum agents in systems of trapped ions. We employ a generic construction by which the classical agents are ‘upgraded’ to their quantum counterparts by a nested process of adding coherent control, and we outline how this construction can be realized in ion traps. Our results provide a flexible modular architecture for the design of PS agents. Furthermore, we present numerical simulations of simple PS agents which analyze the robustness of our proposal under certain noise models.

In Situ Preparation of Polyether Amine Functionalized MWCNT Nanofiller as Reinforcing Agents

Directory of Open Access Journals (Sweden)

Ayber Yıldrım

2014-01-01

Full Text Available In situ preparation of polyether amine functionalized cross-linked multiwalled carbon nanotube (MWCNT nanofillers may improve the thermal and mechanical properties of the composites in which they are used as reinforcing agents. The reduction and functionalization of MWCNT using ethylenediamine in the presence of polyether amine produced stitched MWCNT's due to the presence of two amine (–NH2 functionalities on both sides of the polymer. Polyether amine was chosen to polymerize the carboxylated MWCNT due to its potential to form bonds with the amino groups and carboxyl groups of MWCNT which produces a resin used as polymeric matrix for nanocomposite materials. The attachment of the polyether amine (Jeffamine groups was verified by TGA, FT-IR, XRD, SEM, and Raman spectroscopy. The temperature at which the curing enthalpy is maximum, observed by DSC, was shifted to higher values by adding functionalized MWCNT. SEM images show the polymer formation between MWCNT sheets.

Using Hierarchical Machine Learning to Improve Player Satisfaction in a Soccer Videogame

OpenAIRE

Collins, Brian; Rovatsos, Michael

2006-01-01

This paper describes an approach to using a hierarchical machine learning model in a two player 3D physics-based soccer video game to improve human player satisfaction. Learning is accomplished at two layers to form a complete game-playing agent such that higher level strategy learning is dependent on lower-level learning of basic behaviors.Supervised learning is used to train neural networks on human data to model the basic behaviors. The reinforcement learning algorithms Sarsa (λ) and Q(λ) ...

Teachable Agents and the Protege Effect: Increasing the Effort towards Learning

Science.gov (United States)

Chase, Catherine C.; Chin, Doris B.; Oppezzo, Marily A.; Schwartz, Daniel L.

2009-01-01

Betty's Brain is a computer-based learning environment that capitalizes on the social aspects of learning. In Betty's Brain, students instruct a character called a Teachable Agent (TA) which can reason based on how it is taught. Two studies demonstrate the "protege effect": students make greater effort to learn for their TAs than they do…

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

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.

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)

Strategies to Enhance Online Learning Teams. Team Assessment and Diagnostics Instrument and Agent-based Modeling

Science.gov (United States)

2010-08-12

Strategies to Enhance Online Learning Teams Team Assessment and Diagnostics Instrument and Agent-based Modeling Tristan E. Johnson, Ph.D. Learning ...REPORT DATE AUG 2010 2. REPORT TYPE 3. DATES COVERED 00-00-2010 to 00-00-2010 4. TITLE AND SUBTITLE Strategies to Enhance Online Learning ...TeamsTeam Strategies to Enhance Online Learning Teams: Team Assessment and Diagnostics Instrument and Agent-based Modeling 5a. CONTRACT NUMBER 5b. GRANT

Quantum-enhanced deliberation of learning agents using trapped ions

International Nuclear Information System (INIS)

Dunjko, V; Friis, N; Briegel, H J

2015-01-01

A scheme that successfully employs quantum mechanics in the design of autonomous learning agents has recently been reported in the context of the projective simulation (PS) model for artificial intelligence. In that approach, the key feature of a PS agent, a specific type of memory which is explored via random walks, was shown to be amenable to quantization, allowing for a speed-up. In this work we propose an implementation of such classical and quantum agents in systems of trapped ions. We employ a generic construction by which the classical agents are ‘upgraded’ to their quantum counterparts by a nested process of adding coherent control, and we outline how this construction can be realized in ion traps. Our results provide a flexible modular architecture for the design of PS agents. Furthermore, we present numerical simulations of simple PS agents which analyze the robustness of our proposal under certain noise models. (paper)

Pedagogical Agents as Learning Companions: Building Social Relations with Learners

OpenAIRE

Kim, Yanghee

2005-01-01

This study examined the potential of pedagogical agents as learning companions (PALs) to build social relations with learners and, consequently, to motivate learning. The study investigated the impact of PAL affect (positive vs. negative vs. neutral), PAL gender (male vs. female), and learner gender (male vs. female) on learners’ social judgments, motivation, and learning in a controlled experiment. Participants were 142 college students in a computer-literacy course. Overall, the results ind...

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)

Quantum machine learning with glow for episodic tasks and decision games

Science.gov (United States)

Clausen, Jens; Briegel, Hans J.

2018-02-01

We consider a general class of models, where a reinforcement learning (RL) agent learns from cyclic interactions with an external environment via classical signals. Perceptual inputs are encoded as quantum states, which are subsequently transformed by a quantum channel representing the agent's memory, while the outcomes of measurements performed at the channel's output determine the agent's actions. The learning takes place via stepwise modifications of the channel properties. They are described by an update rule that is inspired by the projective simulation (PS) model and equipped with a glow mechanism that allows for a backpropagation of policy changes, analogous to the eligibility traces in RL and edge glow in PS. In this way, the model combines features of PS with the ability for generalization, offered by its physical embodiment as a quantum system. We apply the agent to various setups of an invasion game and a grid world, which serve as elementary model tasks allowing a direct comparison with a basic classical PS agent.

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.

Neural modularity helps organisms evolve to learn new skills without forgetting old skills.

Science.gov (United States)

Ellefsen, Kai Olav; Mouret, Jean-Baptiste; Clune, Jeff

2015-04-01

A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks are organized critically affects their learning dynamics. In this paper, we test whether catastrophic forgetting can be reduced by evolving modular neural networks. Modularity intuitively should reduce learning interference between tasks by separating functionality into physically distinct modules in which learning can be selectively turned on or off. Modularity can further improve learning by having a reinforcement learning module separate from sensory processing modules, allowing learning to happen only in response to a positive or negative reward. In this paper, learning takes place via neuromodulation, which allows agents to selectively change the rate of learning for each neural connection based on environmental stimuli (e.g. to alter learning in specific locations based on the task at hand). To produce modularity, we evolve neural networks with a cost for neural connections. We show that this connection cost technique causes modularity, confirming a previous result, and that such sparsely connected, modular networks have higher overall performance because they learn new skills faster while retaining old skills more and because they have a separate reinforcement learning module. Our results suggest (1) that encouraging modularity in neural networks may help us overcome the long-standing barrier of networks that cannot learn new skills without forgetting old ones, and (2) that one benefit of the modularity ubiquitous in the brains of natural animals might be to

Neural modularity helps organisms evolve to learn new skills without forgetting old skills.

Directory of Open Access Journals (Sweden)

Kai Olav Ellefsen

2015-04-01

Full Text Available A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks are organized critically affects their learning dynamics. In this paper, we test whether catastrophic forgetting can be reduced by evolving modular neural networks. Modularity intuitively should reduce learning interference between tasks by separating functionality into physically distinct modules in which learning can be selectively turned on or off. Modularity can further improve learning by having a reinforcement learning module separate from sensory processing modules, allowing learning to happen only in response to a positive or negative reward. In this paper, learning takes place via neuromodulation, which allows agents to selectively change the rate of learning for each neural connection based on environmental stimuli (e.g. to alter learning in specific locations based on the task at hand. To produce modularity, we evolve neural networks with a cost for neural connections. We show that this connection cost technique causes modularity, confirming a previous result, and that such sparsely connected, modular networks have higher overall performance because they learn new skills faster while retaining old skills more and because they have a separate reinforcement learning module. Our results suggest (1 that encouraging modularity in neural networks may help us overcome the long-standing barrier of networks that cannot learn new skills without forgetting old ones, and (2 that one benefit of the modularity ubiquitous in the brains of natural animals

Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills

Science.gov (United States)

Ellefsen, Kai Olav; Mouret, Jean-Baptiste; Clune, Jeff

2015-01-01

A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks are organized critically affects their learning dynamics. In this paper, we test whether catastrophic forgetting can be reduced by evolving modular neural networks. Modularity intuitively should reduce learning interference between tasks by separating functionality into physically distinct modules in which learning can be selectively turned on or off. Modularity can further improve learning by having a reinforcement learning module separate from sensory processing modules, allowing learning to happen only in response to a positive or negative reward. In this paper, learning takes place via neuromodulation, which allows agents to selectively change the rate of learning for each neural connection based on environmental stimuli (e.g. to alter learning in specific locations based on the task at hand). To produce modularity, we evolve neural networks with a cost for neural connections. We show that this connection cost technique causes modularity, confirming a previous result, and that such sparsely connected, modular networks have higher overall performance because they learn new skills faster while retaining old skills more and because they have a separate reinforcement learning module. Our results suggest (1) that encouraging modularity in neural networks may help us overcome the long-standing barrier of networks that cannot learn new skills without forgetting old ones, and (2) that one benefit of the modularity ubiquitous in the brains of natural animals might be to

Developing multimodal conversational agents for an enhanced e-learning experience

Directory of Open Access Journals (Sweden)

David GRIOL

2014-10-01

Full Text Available Conversational agents have become a strong alternative to enhance educational systems with intelligent communicative capabilities, provide motivation and engagement, and increment significant learning and helping in the acquisition of meta-cognitive skills. In this paper, we present Geranium, a multimodal conversational agent that helps children to appreciate and protect their environment. The system, which integrates an interactive chatbot, has been developed by means of a modular and scalable framework that eases building pedagogic conversational agents that can interact with the students using speech and natural language.

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.

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

The Reinforcement of Pesantren as Harmonization Agent of Religious Life in Pesantren “AL-FATAH” Singkawang, West Kalimantan

Directory of Open Access Journals (Sweden)

Lailial Muhtifah

2016-12-01

Full Text Available This article is to explore the reinforcement of Pesantren as harmonization agent of religious life, the foundation, strategies, procedures, and the assessment process of harmonization in pesantren "AL-FATAH" Singkawang West Kalimantan. The result of the study discovered that harmonization of religious life was based on the philosophical foundation of Islamic values (Islamic brotherhood/ukhuwwah Islamiyah, crossed-marriage, and collective system/jama’ah, foundation of national perspectives (Pancasila, the 1945 Constitution, NKRI, and Bhineka Tunggal Ika and theoretical foundation (Islamic education, social culture, character education and the theory of conflict. Strengthening the strategy of harmonization through the achievement of the objectives, planning, the realization of activity in the form of concrete action, the existence of material, media, sequences and well-managed steps. Procedures of harmonization was applied through approach of method and technique, as reinforcement of pesantren as the harmonization agent of religions life. The assessment process of harmonization has not been carried out properly. The foundations, strategies, procedures and process of assessment have an impact on the emergence of P3AHKB culture and its implementation model. P3AHKB culture is the growth and the development of religious/spiritual values, honesty, responsibility, ukhuwwah Islamiyah, cooperation, empathy, social solidarity, respect, love, protect each other, get used to the language of the sunnah, keeping ethics, the formation of security culture, and rising prosperity with its business units and BMT. The implementation model is named "MI-P3AHKB tree."

Smart Residential Buildings as Learning Agent Organizations in the Internet of Things

Directory of Open Access Journals (Sweden)

Schatten Markus

2014-03-01

Full Text Available Background: Smart buildings are one of the major application areas of technologies bound to embedded systems and the Internet of things. Such systems have to be adaptable and flexible in order to provide better services to its residents. Modelling such systems is an open research question. Herein, the question is approached using an organizational modelling methodology bound to the principles of the learning organization. Objectives: Providing a higher level of abstraction for understanding, developing and maintaining smart residential buildings in a more human understandable form. Methods/Approach: Organization theory provides us with the necessary concepts and methodology to approach complex organizational systems. Results: A set of principles for building learning agent organizations, a formalization of learning processes for agents, a framework for modelling knowledge transfer between agents and the environment, and a tailored organizational structure for smart residential buildings based on Nonaka’s hypertext organizational form. Conclusions: Organization theory is a promising field of research when dealing with complex engineering systems

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.

Adventitious agents in viral vaccines: lessons learned from 4 case studies.

Science.gov (United States)

Petricciani, John; Sheets, Rebecca; Griffiths, Elwyn; Knezevic, Ivana

2014-09-01

Since the earliest days of biological product manufacture, there have been a number of instances where laboratory studies provided evidence for the presence of adventitious agents in a marketed product. Lessons learned from such events can be used to strengthen regulatory preparedness for the future. We have therefore selected four instances where an adventitious agent, or a signal suggesting the presence of an agent, was found in a viral vaccine, and have developed a case study for each. The four cases are: a) SV40 in polio vaccines; b) bacteriophage in measles and polio vaccines; c) reverse transcriptase in measles and mumps vaccines; and d) porcine circovirus and porcine circovirus DNA sequences in rotavirus vaccines. The lessons learned from each event are discussed. Based in part on those experiences, certain scientific principles have been identified by WHO that should be considered in regulatory risk evaluation if an adventitious agent is found in a marketed vaccine in the future. Copyright © 2014 The Authors. Published by Elsevier Ltd.. All rights reserved.

Opinion dynamics of learning agents: does seeking consensus lead to disagreement?

International Nuclear Information System (INIS)

Vicente, Renato; Martins, André C R; Caticha, Nestor

2009-01-01

We study opinion dynamics in a population of interacting adaptive agents voting on a set of issues represented by vectors. We consider agents who can classify issues into one of two categories and can arrive at their opinions using an adaptive algorithm. Adaptation comes from learning and the information for the learning process comes from interacting with other neighboring agents and trying to change the internal state in order to concur with their opinions. The change in the internal state is driven by the information contained in the issue and in the opinion of the other agent. We present results in a simple yet rich context where each agent uses a Boolean perceptron to state their opinion. If the update occurs with information asynchronously exchanged among pairs of agents, then the typical case, if the number of issues is kept small, is the evolution into a society torn by the emergence of factions with extreme opposite beliefs. This occurs even when seeking consensus with agents with opposite opinions. If the number of issues is large, the dynamics becomes trapped, the society does not evolve into factions and a distribution of moderate opinions is observed. The synchronous case is technically simpler and is studied by formulating the problem in terms of differential equations that describe the evolution of order parameters that measure the consensus between pairs of agents. We show that for a large number of issues and unidirectional information flow, global consensus is a fixed point; however, the approach to this consensus is glassy for large societies

Opinion dynamics of learning agents: does seeking consensus lead to disagreement?

Science.gov (United States)

Vicente, Renato; Martins, André C. R.; Caticha, Nestor

2009-03-01

We study opinion dynamics in a population of interacting adaptive agents voting on a set of issues represented by vectors. We consider agents who can classify issues into one of two categories and can arrive at their opinions using an adaptive algorithm. Adaptation comes from learning and the information for the learning process comes from interacting with other neighboring agents and trying to change the internal state in order to concur with their opinions. The change in the internal state is driven by the information contained in the issue and in the opinion of the other agent. We present results in a simple yet rich context where each agent uses a Boolean perceptron to state their opinion. If the update occurs with information asynchronously exchanged among pairs of agents, then the typical case, if the number of issues is kept small, is the evolution into a society torn by the emergence of factions with extreme opposite beliefs. This occurs even when seeking consensus with agents with opposite opinions. If the number of issues is large, the dynamics becomes trapped, the society does not evolve into factions and a distribution of moderate opinions is observed. The synchronous case is technically simpler and is studied by formulating the problem in terms of differential equations that describe the evolution of order parameters that measure the consensus between pairs of agents. We show that for a large number of issues and unidirectional information flow, global consensus is a fixed point; however, the approach to this consensus is glassy for large societies.

Learning to make collective decisions: the impact of confidence escalation.

Science.gov (United States)

Mahmoodi, Ali; Bang, Dan; Ahmadabadi, Majid Nili; Bahrami, Bahador

2013-01-01

Little is known about how people learn to take into account others' opinions in joint decisions. To address this question, we combined computational and empirical approaches. Human dyads made individual and joint visual perceptual decision and rated their confidence in those decisions (data previously published). We trained a reinforcement (temporal difference) learning agent to get the participants' confidence level and learn to arrive at a dyadic decision by finding the policy that either maximized the accuracy of the model decisions or maximally conformed to the empirical dyadic decisions. When confidences were shared visually without verbal interaction, RL agents successfully captured social learning. When participants exchanged confidences visually and interacted verbally, no collective benefit was achieved and the model failed to predict the dyadic behaviour. Behaviourally, dyad members' confidence increased progressively and verbal interaction accelerated this escalation. The success of the model in drawing collective benefit from dyad members was inversely related to confidence escalation rate. The findings show an automated learning agent can, in principle, combine individual opinions and achieve collective benefit but the same agent cannot discount the escalation suggesting that one cognitive component of collective decision making in human may involve discounting of overconfidence arising from interactions.

Designing Multimedia Learning Environments Using Animated Pedagogical Agents: Factors and Issues

Science.gov (United States)

Woo, H. L.

2009-01-01

Animated pedagogical agents (APAs) are known to possess great potential in supporting learning because of their ability to simulate a real classroom learning environment. But research in this area has produced mixed results. The reason for this remains puzzling. This paper is written with two purposes: (1) to examine some recent research and…

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.

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.

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.

Neural systems underlying aversive conditioning in humans with primary and secondary reinforcers

Directory of Open Access Journals (Sweden)

Mauricio R Delgado

2011-05-01

Full Text Available Money is a secondary reinforcer commonly used across a range of disciplines in experimental paradigms investigating reward learning and decision-making. The effectiveness of monetary reinforcers during aversive learning and its neural basis, however, remains a topic of debate. Specifically, it is unclear if the initial acquisition of aversive representations of monetary losses depends on similar neural systems as more traditional aversive conditioning that involves primary reinforcers. This study contrasts the efficacy of a biologically defined primary reinforcer (shock and a socially defined secondary reinforcer (money during aversive learning and its associated neural circuitry. During a two-part experiment, participants first played a gambling game where wins and losses were based on performance to gain an experimental bank. Participants were then exposed to two separate aversive conditioning sessions. In one session, a primary reinforcer (mild shock served as an unconditioned stimulus (US and was paired with one of two colored squares, the conditioned stimuli (CS+ and CS-, respectively. In another session, a secondary reinforcer (loss of money served as the US and was paired with one of two different CS. Skin conductance responses were greater for CS+ compared to CS- trials irrespective of type of reinforcer. Neuroimaging results revealed that the striatum, a region typically linked with reward-related processing, was found to be involved in the acquisition of aversive conditioned response irrespective of reinforcer type. In contrast, the amygdala was involved during aversive conditioning with primary reinforcers, as suggested by both an exploratory fMRI analysis and a follow-up case study with a patient with bilateral amygdala damage. Taken together, these results suggest that learning about potential monetary losses may depend on reinforcement learning related systems, rather than on typical structures involved in more biologically based

A self-taught artificial agent for multi-physics computational model personalization.

Science.gov (United States)

Neumann, Dominik; Mansi, Tommaso; Itu, Lucian; Georgescu, Bogdan; Kayvanpour, Elham; Sedaghat-Hamedani, Farbod; Amr, Ali; Haas, Jan; Katus, Hugo; Meder, Benjamin; Steidl, Stefan; Hornegger, Joachim; Comaniciu, Dorin

2016-12-01

Personalization is the process of fitting a model to patient data, a critical step towards application of multi-physics computational models in clinical practice. Designing robust personalization algorithms is often a tedious, time-consuming, model- and data-specific process. We propose to use artificial intelligence concepts to learn this task, inspired by how human experts manually perform it. The problem is reformulated in terms of reinforcement learning. In an off-line phase, Vito, our self-taught artificial agent, learns a representative decision process model through exploration of the computational model: it learns how the model behaves under change of parameters. The agent then automatically learns an optimal strategy for on-line personalization. The algorithm is model-independent; applying it to a new model requires only adjusting few hyper-parameters of the agent and defining the observations to match. The full knowledge of the model itself is not required. Vito was tested in a synthetic scenario, showing that it could learn how to optimize cost functions generically. Then Vito was applied to the inverse problem of cardiac electrophysiology and the personalization of a whole-body circulation model. The obtained results suggested that Vito could achieve equivalent, if not better goodness of fit than standard methods, while being more robust (up to 11% higher success rates) and with faster (up to seven times) convergence rate. Our artificial intelligence approach could thus make personalization algorithms generalizable and self-adaptable to any patient and any model. Copyright © 2016. Published by Elsevier B.V.

Linguistic Models at the Crossroads of Agents, Learning and Formal Languages

Directory of Open Access Journals (Sweden)

Leonor BECERRA-BONACHE

2014-12-01

Full Text Available This paper aims at reviewing the most relevant linguistic applications developed in the intersection between three different fields: machine learning, formal language theory and agent technologies. On the one hand, we present some of the main linguistic contributions of the intersection between machine learning and formal languages, which constitutes a well-established research area known as Grammatical Inference. On the other hand, we present an overview of the main linguistic applications of models developed in the intersection between agent technologies and formal languages, such as colonies, grammar systems and eco-grammar systems. Our goal is to show how interdisciplinary research between these three fields can contribute to better understand how natural language is acquired and processed.

Mirror Neurons, Embodied Cognitive Agents and Imitation Learning

Czech Academy of Sciences Publication Activity Database

Wiedermann, Jiří

2003-01-01

Roč. 22, č. 6 (2003), s. 545-559 ISSN 1335-9150 R&D Projects: GA ČR GA201/02/1456 Institutional research plan: CEZ:AV0Z1030915 Keywords : complete agents * mirror neurons * embodied cognition * imitation learning * sensorimotor control Subject RIV: BA - General Mathematics Impact factor: 0.254, year: 2003 http://www.cai.sk/ojs/index.php/cai/article/view/468

N-grams Based Supervised Machine Learning Model for Mobile Agent Platform Protection against Unknown Malicious Mobile Agents

Directory of Open Access Journals (Sweden)

Pallavi Bagga

2017-12-01

Full Text Available From many past years, the detection of unknown malicious mobile agents before they invade the Mobile Agent Platform has been the subject of much challenging activity. The ever-growing threat of malicious agents calls for techniques for automated malicious agent detection. In this context, the machine learning (ML methods are acknowledged more effective than the Signature-based and Behavior-based detection methods. Therefore, in this paper, the prime contribution has been made to detect the unknown malicious mobile agents based on n-gram features and supervised ML approach, which has not been done so far in the sphere of the Mobile Agents System (MAS security. To carry out the study, the n-grams ranging from 3 to 9 are extracted from a dataset containing 40 malicious and 40 non-malicious mobile agents. Subsequently, the classification is performed using different classifiers. A nested 5-fold cross validation scheme is employed in order to avoid the biasing in the selection of optimal parameters of classifier. The observations of extensive experiments demonstrate that the work done in this paper is suitable for the task of unknown malicious mobile agent detection in a Mobile Agent Environment, and also adds the ML in the interest list of researchers dealing with MAS security.

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.

Visual reinforcement shapes eye movements in visual search.

Science.gov (United States)

Paeye, Céline; Schütz, Alexander C; Gegenfurtner, Karl R

2016-08-01

We use eye movements to gain information about our visual environment; this information can indirectly be used to affect the environment. Whereas eye movements are affected by explicit rewards such as points or money, it is not clear whether the information gained by finding a hidden target has a similar reward value. Here we tested whether finding a visual target can reinforce eye movements in visual search performed in a noise background, which conforms to natural scene statistics and contains a large number of possible target locations. First we tested whether presenting the target more often in one specific quadrant would modify eye movement search behavior. Surprisingly, participants did not learn to search for the target more often in high probability areas. Presumably, participants could not learn the reward structure of the environment. In two subsequent experiments we used a gaze-contingent display to gain full control over the reinforcement schedule. The target was presented more often after saccades into a specific quadrant or a specific direction. The proportions of saccades meeting the reinforcement criteria increased considerably, and participants matched their search behavior to the relative reinforcement rates of targets. Reinforcement learning seems to serve as the mechanism to optimize search behavior with respect to the statistics of the task.

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.

The chemotherapeutic agent paclitaxel selectively impairs reversal learning while sparing prior learning, new learning and episodic memory.

Science.gov (United States)

Panoz-Brown, Danielle; Carey, Lawrence M; Smith, Alexandra E; Gentry, Meredith; Sluka, Christina M; Corbin, Hannah E; Wu, Jie-En; Hohmann, Andrea G; Crystal, Jonathon D

2017-10-01

Chemotherapy is widely used to treat patients with systemic cancer. The efficacy of cancer therapies is frequently undermined by adverse side effects that have a negative impact on the quality of life of cancer survivors. Cancer patients who receive chemotherapy often experience chemotherapy-induced cognitive impairment across a variety of domains including memory, learning, and attention. In the current study, the impact of paclitaxel, a taxane derived chemotherapeutic agent, on episodic memory, prior learning, new learning, and reversal learning were evaluated in rats. Neurogenesis was quantified post-treatment in the dentate gyrus of the same rats using immunostaining for 5-Bromo-2'-deoxyuridine (BrdU) and Ki67. Paclitaxel treatment selectively impaired reversal learning while sparing episodic memory, prior learning, and new learning. Furthermore, paclitaxel-treated rats showed decreases in markers of hippocampal cell proliferation, as measured by markers of cell proliferation assessed using immunostaining for Ki67 and BrdU. This work highlights the importance of using multiple measures of learning and memory to identify the pattern of impaired and spared aspects of chemotherapy-induced cognitive impairment. Copyright © 2017 Elsevier Inc. All rights reserved.

Vicarious Reinforcement In Rhesus Macaques (Macaca mulatta

Directory of Open Access Journals (Sweden)

Steve W. C. Chang

2011-03-01

Full Text Available What happens to others profoundly influences our own behavior. Such other-regarding outcomes can drive observational learning, as well as motivate cooperation, charity, empathy, and even spite. Vicarious reinforcement may serve as one of the critical mechanisms mediating the influence of other-regarding outcomes on behavior and decision-making in groups. Here we show that rhesus macaques spontaneously derive vicarious reinforcement from observing rewards given to another monkey, and that this reinforcement can motivate them to subsequently deliver or withhold rewards from the other animal. We exploited Pavlovian and instrumental conditioning to associate rewards to self (M1 and/or rewards to another monkey (M2 with visual cues. M1s made more errors in the instrumental trials when cues predicted reward to M2 compared to when cues predicted reward to M1, but made even more errors when cues predicted reward to no one. In subsequent preference tests between pairs of conditioned cues, M1s preferred cues paired with reward to M2 over cues paired with reward to no one. By contrast, M1s preferred cues paired with reward to self over cues paired with reward to both monkeys simultaneously. Rates of attention to M2 strongly predicted the strength and valence of vicarious reinforcement. These patterns of behavior, which were absent in nonsocial control trials, are consistent with vicarious reinforcement based upon sensitivity to observed, or counterfactual, outcomes with respect to another individual. Vicarious reward may play a critical role in shaping cooperation and competition, as well as motivating observational learning and group coordination in rhesus macaques, much as it does in humans. We propose that vicarious reinforcement signals mediate these behaviors via homologous neural circuits involved in reinforcement learning and decision-making.

Vicarious reinforcement in rhesus macaques (macaca mulatta).

Science.gov (United States)

Chang, Steve W C; Winecoff, Amy A; Platt, Michael L

2011-01-01

What happens to others profoundly influences our own behavior. Such other-regarding outcomes can drive observational learning, as well as motivate cooperation, charity, empathy, and even spite. Vicarious reinforcement may serve as one of the critical mechanisms mediating the influence of other-regarding outcomes on behavior and decision-making in groups. Here we show that rhesus macaques spontaneously derive vicarious reinforcement from observing rewards given to another monkey, and that this reinforcement can motivate them to subsequently deliver or withhold rewards from the other animal. We exploited Pavlovian and instrumental conditioning to associate rewards to self (M1) and/or rewards to another monkey (M2) with visual cues. M1s made more errors in the instrumental trials when cues predicted reward to M2 compared to when cues predicted reward to M1, but made even more errors when cues predicted reward to no one. In subsequent preference tests between pairs of conditioned cues, M1s preferred cues paired with reward to M2 over cues paired with reward to no one. By contrast, M1s preferred cues paired with reward to self over cues paired with reward to both monkeys simultaneously. Rates of attention to M2 strongly predicted the strength and valence of vicarious reinforcement. These patterns of behavior, which were absent in non-social control trials, are consistent with vicarious reinforcement based upon sensitivity to observed, or counterfactual, outcomes with respect to another individual. Vicarious reward may play a critical role in shaping cooperation and competition, as well as motivating observational learning and group coordination in rhesus macaques, much as it does in humans. We propose that vicarious reinforcement signals mediate these behaviors via homologous neural circuits involved in reinforcement learning and decision-making.

Fiber-Reinforced Epoxy Composites and Methods of Making Same Without the Use of Oven or Autoclave

Science.gov (United States)

Barnell, Thomas J. (Inventor); Rauscher, Michael D. (Inventor); Stienecker, Rick D. (Inventor); Nickerson, David M. (Inventor); Tong, Tat H. (Inventor)

2016-01-01

Method embodiments for producing a fiber-reinforced epoxy composite comprise providing a mold defining a shape for a composite, applying a fiber reinforcement over the mold, covering the mold and fiber reinforcement thereon in a vacuum enclosure, performing a vacuum on the vacuum enclosure to produce a pressure gradient, insulating at least a portion of the vacuum enclosure with thermal insulation, infusing the fiber reinforcement with a reactive mixture of uncured epoxy resin and curing agent under vacuum conditions, wherein the reactive mixture of uncured epoxy resin and curing agent generates exothermic heat, and producing the fiber-reinforced epoxy composite having a glass transition temperature of at least about 100.degree. C. by curing the fiber reinforcement infused with the reactive mixture of uncured epoxy resin and curing agent by utilizing the exothermically generated heat, wherein the curing is conducted inside the thermally insulated vacuum enclosure without utilization of an external heat source or an external radiation source.

A learning-based agent for home neurorehabilitation.

Science.gov (United States)

Lydakis, Andreas; Meng, Yuanliang; Munroe, Christopher; Wu, Yi-Ning; Begum, Momotaz

2017-07-01

This paper presents the iterative development of an artificially intelligent system to promote home-based neurorehabilitation. Although proper, structured practice of rehabilitation exercises at home is the key to successful recovery of motor functions, there is no home-program out there which can monitor a patient's exercise-related activities and provide corrective feedback in real time. To this end, we designed a Learning from Demonstration (LfD) based home-rehabilitation framework that combines advanced robot learning algorithms with commercially available wearable technologies. The proposed system uses exercise-related motion information and electromyography signals (EMG) of a patient to train a Markov Decision Process (MDP). The trained MDP model can enable an agent to serve as a coach for a patient. On a system level, this is the first initiative, to the best of our knowledge, to employ LfD in an health-care application to enable lay users to program an intelligent system. From a rehabilitation research perspective, this is a completely novel initiative to employ machine learning to provide interactive corrective feedback to a patient in home settings.

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.

Silica reinforced triblock copolymer gels

DEFF Research Database (Denmark)

Theunissen, E.; Overbergh, N.; Reynaers, H.

2004-01-01

The effect of silica and polymer coated silica particles as reinforcing agents on the structural and mechanical properties of polystyrene-poly(ethylene/butylene)-polystyrene (PS-PEB-PS) triblock gel has been investigated. Different types of chemically modified silica have been compared in order...

Agent-oriented Modeling for Collaborative Learning Environments: A Peer-to-Peer Helpdesk Case Study

NARCIS (Netherlands)

Guizzardi-Silva Souza, R.; Wagner, G.; Aroyo, L.M.

2002-01-01

In this paper, we present the analysis and modelling of Help&Learn, an agent-based peer-to-peer helpdesk system to support extra-class interactions among students and teachers. Help&Learn expands the student’s possibility of solving problems, getting involved in a cooperative learning experience

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.

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.

Distributed scheduling for autonomous vehicles by reinforcement learning; Kyoka gakushu ni yoru mujin hansosha no bunsangata scheduling

Energy Technology Data Exchange (ETDEWEB)

Unoki, T.; Suetake, N. [Oki Electric Industry Co. Ltd., Tokyo (Japan)

1997-08-20

In this paper, we propose an autonomous vehicle scheduling schema in large physical distribution terminals publicly used as the next generation wide area physical distribution bases. This schema uses Learning Automaton for vehicles scheduling based on Contract Net Protocol, in order to obtain useful emergent behaviors of agents in the system based on the local decision-making of each agent. The state of the automaton is updated at each instant on the basis of new information that includes the arrival estimation time of vehicles. Each agent estimates the arrival time of vehicles by using Bayesian learning process. Using traffic simulation, we evaluate the schema in various simulated environments. The result shows the advantage of the schema over when each agent provides the same criteria from the top down, and each agent voluntarily generates criteria via interactions with the environment, playing an individual role in tie system. 22 refs., 5 figs., 2 tabs.

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.

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.

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.

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.

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.

Activity in the superior temporal sulcus highlights learning competence in an interaction game.

Science.gov (United States)

Haruno, Masahiko; Kawato, Mitsuo

2009-04-08

During behavioral adaptation through interaction with human and nonhuman agents, marked individual differences are seen in both real-life situations and games. However, the underlying neural mechanism is not well understood. We conducted a neuroimaging experiment in which subjects maximized monetary rewards by learning in a prisoner's dilemma game with two computer agents: agent A, a tit-for-tat player who repeats the subject's previous action, and agent B, a simple stochastic cooperator oblivious to the subject's action. Approximately 1/3 of the subjects (group I) learned optimally in relation to both A and B, while another 1/3 (group II) did so only for B. Post-experiment interviews indicated that group I exploited the agent strategies more often than group II. Significant differences in learning-related brain activity between the two groups were only found in the superior temporal sulcus (STS) for both A and B. Furthermore, the learning performance of each group I subject was predictable based on this STS activity, but not in the group II subjects. This differential activity could not be attributed to a behavioral difference since it persisted in relation to agent B for which the two groups behaved similarly. In sharp contrast, the brain structures for reward processing were recruited similarly by both groups. These results suggest that STS provides knowledge of the other agent's strategies for association between action and reward and highlights learning competence during interactive reinforcement learning.

A theoretical analysis of temporal difference learning in the iterated prisoner's dilemma game.

Science.gov (United States)

Masuda, Naoki; Ohtsuki, Hisashi

2009-11-01

Direct reciprocity is a chief mechanism of mutual cooperation in social dilemma. Agents cooperate if future interactions with the same opponents are highly likely. Direct reciprocity has been explored mostly by evolutionary game theory based on natural selection. Our daily experience tells, however, that real social agents including humans learn to cooperate based on experience. In this paper, we analyze a reinforcement learning model called temporal difference learning and study its performance in the iterated Prisoner's Dilemma game. Temporal difference learning is unique among a variety of learning models in that it inherently aims at increasing future payoffs, not immediate ones. It also has a neural basis. We analytically and numerically show that learners with only two internal states properly learn to cooperate with retaliatory players and to defect against unconditional cooperators and defectors. Four-state learners are more capable of achieving a high payoff against various opponents. Moreover, we numerically show that four-state learners can learn to establish mutual cooperation for sufficiently small learning rates.

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.

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...

Evolving Neural Turing Machines for Reward-based Learning

DEFF Research Database (Denmark)

Greve, Rasmus Boll; Jacobsen, Emil Juul; Risi, Sebastian

2016-01-01

An unsolved problem in neuroevolution (NE) is to evolve artificial neural networks (ANN) that can store and use information to change their behavior online. While plastic neural networks have shown promise in this context, they have difficulties retaining information over longer periods of time...... version of the double T-Maze, a complex reinforcement-like learning problem. In the T-Maze learning task the agent uses the memory bank to display adaptive behavior that normally requires a plastic ANN, thereby suggesting a complementary and effective mechanism for adaptive behavior in NE....

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.

An Autonomous Mobile Agent-Based Distributed Learning Architecture-A Proposal and Analytical Analysis

Directory of Open Access Journals (Sweden)

I. Ahmed M. J. SADIIG

2005-10-01

Full Text Available An Autonomous Mobile Agent-Based Distributed Learning Architecture-A Proposal and Analytical Analysis Dr. I. Ahmed M. J. SADIIG Department of Electrical & Computer EngineeringInternational Islamic University GombakKuala Lumpur-MALAYSIA ABSTRACT The traditional learning paradigm invoving face-to-face interaction with students is shifting to highly data-intensive electronic learning with the advances in Information and Communication Technology. An important component of the e-learning process is the delivery of the learning contents to their intended audience over a network. A distributed learning system is dependent on the network for the efficient delivery of its contents to the user. However, as the demand of information provision and utilization increases on the Internet, the current information service provision and utilization methods are becoming increasingly inefficient. Although new technologies have been employed for efficient learning methodologies within the context of an e-learning environment, the overall efficiency of the learning system is dependent on the mode of distribution and utilization of its learning contents. It is therefore imperative to employ new techniques to meet the service demands of current and future e-learning systems. In this paper, an architecture based on autonomous mobile agents creating a Faded Information Field is proposed. Unlike the centralized information distribution in a conventional e-learning system, the information is decentralized in the proposed architecture resulting in increased efficiency of the overall system for distribution and utilization of system learning contents efficiently and fairly. This architecture holds the potential to address the heterogeneous user requirements as well as the changing conditions of the underlying network.

The partial-reinforcement extinction effect and the contingent-sampling hypothesis.

Science.gov (United States)

Hochman, Guy; Erev, Ido

2013-12-01

The partial-reinforcement extinction effect (PREE) implies that learning under partial reinforcements is more robust than learning under full reinforcements. While the advantages of partial reinforcements have been well-documented in laboratory studies, field research has failed to support this prediction. In the present study, we aimed to clarify this pattern. Experiment 1 showed that partial reinforcements increase the tendency to select the promoted option during extinction; however, this effect is much smaller than the negative effect of partial reinforcements on the tendency to select the promoted option during the training phase. Experiment 2 demonstrated that the overall effect of partial reinforcements varies inversely with the attractiveness of the alternative to the promoted behavior: The overall effect is negative when the alternative is relatively attractive, and positive when the alternative is relatively unattractive. These results can be captured with a contingent-sampling model assuming that people select options that provided the best payoff in similar past experiences. The best fit was obtained under the assumption that similarity is defined by the sequence of the last four outcomes.

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

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

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...

A framework for learning and planning against switching strategies in repeated games

Science.gov (United States)

Hernandez-Leal, Pablo; Munoz de Cote, Enrique; Sucar, L. Enrique

2014-04-01

Intelligent agents, human or artificial, often change their behaviour as they interact with other agents. For an agent to optimise its performance when interacting with such agents, it must be capable of detecting and adapting according to such changes. This work presents an approach on how to effectively deal with non-stationary switching opponents in a repeated game context. Our main contribution is a framework for online learning and planning against opponents that switch strategies. We present how two opponent modelling techniques work within the framework and prove the usefulness of the approach experimentally in the iterated prisoner's dilemma, when the opponent is modelled as an agent that switches between different strategies (e.g. TFT, Pavlov and Bully). The results of both models were compared against each other and against a state-of-the-art non-stationary reinforcement learning technique. Results reflect that our approach obtains competitive results without needing an offline training phase, as opposed to the state-of-the-art techniques.

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.

An agent architecture with on-line learning of both procedural and declarative knowledge

Energy Technology Data Exchange (ETDEWEB)

Sun, R.; Peterson, T.; Merrill, E. [Univ. of Alabama, Tuscaloosa, AL (United States)

1996-12-31

In order to develop versatile cognitive agents that learn in situated contexts and generalize resulting knowledge to different environments, we explore the possibility of learning both declarative and procedural knowledge in a hybrid connectionist architecture. The architecture is based on the two-level idea proposed earlier by the author. Declarative knowledge is represented symbolically, while procedural knowledge is represented subsymbolically. The architecture integrates reactive procedures, rules, learning, and decision-making in a unified framework, and structures different learning components (including Q-learning and rule induction) in a synergistic way to perform on-line and integrated learning.

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.

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

Fostering Multimedia Learning of Science: Exploring the Role of an Animated Agent's Image

Science.gov (United States)

Dunsworth, Qi; Atkinson, Robert K.

2007-01-01

Research suggests that students learn better when studying a picture coupled with narration rather than on-screen text in a computer-based multimedia learning environment. Moreover, combining narration with the visual presence of an animated pedagogical agent may also encourage students to process information deeper than narration or on-screen…

Mirror Neurons, Embodied Cognitive Agents and Imitation Learning

OpenAIRE

Wiedermann, Jiří

2003-01-01

Mirror neurons are a relatively recent discovery; it has been conjectured that these neurons play an important role in imitation learning and other cognitive phenomena. We will study a possible place and role of mirror neurons in the neural architecture of embodied cognitive agents. We will formulate and investigate the hypothesis that mirror neurons serve as a mechanism which coordinates the multimodal (i.e., motor, perceptional and proprioceptive) information and completes it so that the ag...

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.

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.

The efficiency of the RULES-4 classification learning algorithm in predicting the density of agents

Directory of Open Access Journals (Sweden)

Ziad Salem

2014-12-01

Full Text Available Learning is the act of obtaining new or modifying existing knowledge, behaviours, skills or preferences. The ability to learn is found in humans, other organisms and some machines. Learning is always based on some sort of observations or data such as examples, direct experience or instruction. This paper presents a classification algorithm to learn the density of agents in an arena based on the measurements of six proximity sensors of a combined actuator sensor units (CASUs. Rules are presented that were induced by the learning algorithm that was trained with data-sets based on the CASU’s sensor data streams collected during a number of experiments with “Bristlebots (agents in the arena (environment”. It was found that a set of rules generated by the learning algorithm is able to predict the number of bristlebots in the arena based on the CASU’s sensor readings with satisfying accuracy.

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.

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.

Determinants of E-learning Acceptance among Agricultural Extension Agents in Malaysia: A Conceptual Framework

OpenAIRE

Mangir, Safaie; Othman, Zakirah; Udin, Zulkifli Mohamed

2016-01-01

The objective of this paper is to develop a framework on e-learning acceptance among agricultural extension agents in Malaysian agricultural sector. E-learning is viewed as a solution in response to the increasing need for learning and training. This paper will review past literatures for the relevant factors that influence behavioral intention for e-learning acceptance as well as the relevant behavioral theories that provide the foundation for developing research framework to illustrate the ...

Cytocompatibility and Mechanical Properties of Short Phosphate Glass Fibre Reinforced Polylactic Acid (PLA Composites: Effect of Coupling Agent Mediated Interface

Directory of Open Access Journals (Sweden)

Gavin Walker

2012-10-01

Full Text Available In this study three chemical agents Amino-propyl-triethoxy-silane (APS, sorbitol ended PLA oligomer (SPLA and Hexamethylene diisocyanate (HDI were identified to be used as coupling agents to react with the phosphate glass fibre (PGF reinforcement and the polylactic acid (PLA polymer matrix of the composite. Composites were prepared with short chopped strand fibres (l = 20 mm, ϕ = 20 µm in a random arrangement within PLA matrix. Improved, initial composite flexural strength (~20 MPa was observed for APS treated fibres, which was suggested to be due to enhanced bonding between the fibres and polymer matrix. Both APS and HDI treated fibres were suggested to be covalently linked with the PLA matrix. The hydrophobicity induced by these coupling agents (HDI, APS helped to resist hydrolysis of the interface and thus retained their mechanical properties for an extended period of time as compared to non-treated control. Approximately 70% of initial strength and 65% of initial modulus was retained by HDI treated fibre composites in contrast to the control, where only ~50% of strength and modulus was retained after 28 days of immersion in PBS at 37 °C. All coupling agent treated and control composites demonstrated good cytocompatibility which was comparable to the tissue culture polystyrene (TCP control, supporting the use of these materials as coupling agent’s within medical implant devices.

Animated pedagogical agents effects on enhancing student motivation and learning in a science inquiry learning environment

NARCIS (Netherlands)

van der Meij, Hans; van der Meij, Jan; Harmsen, Ruth

This study focuses on the design and testing of a motivational animated pedagogical agent (APA) in an inquiry learning environment on kinematics. The aim of including the APA was to enhance students’ perceptions of task relevance and selfefficacy. Given the under-representation of girls in science

Animated pedagogical agents effects on enhancing student motivation and learning in a science inquiry learning environment

NARCIS (Netherlands)

van der Meij, Hans; van der Meij, Jan; Harmsen, Ruth

2015-01-01

This study focuses on the design and testing of a motivational animated pedagogical agent (APA) in an inquiry learning environment on kinematics. The aim of including the APA was to enhance students’ perceptions of task relevance and self-efficacy. Given the under-representation of girls in science

The Cost of Performance? Students' Learning about Acting as Change Agents in Their Schools

Science.gov (United States)

Kehoe, Ian

2015-01-01

This paper explores how performance culture could affect students' learning about, and disposition towards, acting as organisational change agents in schools. This is based on findings from an initiative aimed to enable students to experience acting as change agents on an aspect of the school's culture that concerned them. The initiative was…

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…

Contrast agents provide a faster learning curve in dipyridamole stress echocardiography.

Science.gov (United States)

Zamorano, Jose; Sánchez, Violeta; Moreno, Raúl; Almería, Carlos; Rodrigo, Jose; Serra, Viviana; Azcona, Luis; Aubele, Adalia; Mataix, Luis; Sánchez-Harguindey, Luis

2002-12-01

Interobserver variability is an important limitation of the stress echocardiography and depends on the echocardiographer training. Our aim was to evaluate if the use of contrast agents during dipyridamole stress echocardiography would improve the agreement between an experienced and a non-experienced observer in stress echo and therefore if contrast would affect the learning period of dypyridamole stress echo. Two independent observers without knowledge of any patient data interpreted all stress studies. One observer was an experienced one and the other had experience in echocardiography but not in stress echo. Two observers analysed 87 non-selected and consecutive studies. Out of the 87 studies, 46 were performed without contrast administration, whereas i.v. contrast (2.5 g Levovist by two bolus at rest and at peak stress) was administered in 41. In all cases, second harmonic imaging and stress digitalisation pack was used. The agreement between observers showed a kappa index of 0.58 and 0.83 without and with contrast administration, respectively. The use of contrast agents provides a better agreement in the evaluation of stress echo between an experienced and a non-experienced observer in stress echo. Adding routinely contrast agents could probably reduce the number of exams required for the necessary learning curve in stress echocardiography.

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.

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.

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

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

Cloud Computing and Multi Agent System to improve Learning Object Paradigm

Directory of Open Access Journals (Sweden)

Ana B. Gil

2015-05-01

Full Text Available The paradigm of Learning Object provides Educators and Learners with the ability to access an extensive number of learning resources. To do so, this paradigm provides different technologies and tools, such as federated search platforms and storage repositories, in order to obtain information ubiquitously and on demand. However, the vast amount and variety of educational content, which is distributed among several repositories, and the existence of various and incompatible standards, technologies and interoperability layers among repositories, constitutes a real problem for the expansion of this paradigm. This study presents an agent-based architecture that uses the advantages provided by Cloud Computing platforms to deal with the open issues on the Learning Object paradigm.