Wiering M., van Otterlo M. (Eds.) Reinforcement Learning: State-of-the-Art

Springer, 2012. — 652 p. — ISBN: 978-3642276446, e-ISBN: 978-3642276453.
Series: Adaptation, Learning, and Optimization (Book 12).Reinforcement learning encompasses both a science of adaptive behavior of rational beings in uncertain environments and a computational methodology for finding optimal behaviors for challenging problems in control, optimization and adaptive behavior of intelligent agents. As a field, reinforcement learning has progressed tremendously in the past decade.
The main goal of this book is to present an up-to-date series of survey articles on the main contemporary sub-fields of reinforcement learning. This includes surveys on partially observable environments, hierarchical task decompositions, relational knowledge representation and predictive state representations. Furthermore, topics such as transfer, evolutionary methods and continuous spaces in reinforcement learning are surveyed. In addition, several chapters review reinforcement learning methods in robotics, in games, and in computational neuroscience. In total seventeen different subfields are presented by mostly young experts in those areas, and together they truly represent a state-of-the-art of current reinforcement learning research.Introductory Part.
Reinforcement Learning and Markov Decision Processes.
Efficient Solution Frameworks.
Batch Reinforcement Learning.
Least-Squares Methods for Policy Iteration.
Learning and Using Models.
Transfer in Reinforcement Learning: A Framework and a Survey.
Sample Complexity Bounds of Exploration.
Constructive-Representational Directions.
Reinforcement Learning in Continuous State and Action Spaces.
Solving Relational and First-Order Logical Markov Decision Processes: A Survey.
Hierarchical Approaches.
Evolutionary Computation for Reinforcement Learning.
Probabilistic Models of Self and Others.
Bayesian Reinforcement Learning.
Partially Observable Markov Decision Processes.
Predictively Defined Representations of State.
Game Theory and Multi-agent Reinforcement Learning.
Decentralized POMDPs.
Domains and Background.
Psychological and Neuroscientific Connections with Reinforcement Learning.
Reinforcement Learning in Games.
Reinforcement Learning in Robotics: A Survey.
Closing.
Conclusions, Future Directions and Outlook.