TY  - BOOK
AU  - Wiering,Marco
AU  - Otterlo,Martijn van
TI  - Reinforcement learning: state-of-the-art 
T2  - Adaptation, learning, and optimization,
SN  - 9783642276446
AV  - Q325.6 .R465 2012
PY  - 2012///
CY  - Heidelberg, New York
PB  - Springer
KW  - Reinforcement learning
KW  - fast
N1  - Includes bibliographical references and index; 1. Reinforcement learning and Markov decision processes / Martijn van Otterlo, Marco Wiering; -- 2. Batch reinforcement learning / Sascha Lange, Thomas Gabel, Martin Riedmiller; -- 3. Least-squares methods for policy iteration / Lucian Buşoniu, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos, Robert Babuška, Bart De Schutter; --  4. Learning and using models / Todd Hester, Peter Stone; -- 5. Transfer in reinforcement learning: a framework and a survey / Alessandro Lazaric; -- 6. Sample complexity bounds of exploration / Lihong Li; -- 7. Reinforcement learning in continuous state and action spaces / Hado van Hasselt; -- 8. Solving relational and first-order logical Markov decision processes: a survey / Martijn van Otterlo; -- 9. Hierarchical approaches / Bernhard Hengst; -- 10. Evolutionary computation for reinforcement learning / Shimon Whiteson; -- 11. Bayesian reinforcement learning / Nikos Vlassis, Mohammad Ghavamzadeh, Shie Mannor, Pascal Poupart; -- 12. Partially observable Markov decision processes / Matthijs T. J. Spaan; -- 13. Predictively defined representations of state / David Wingate; -- 14. Game theory and multi-agent reinforcement learning / Ann Nowé, Peter Vrancx, Yann-Michaël De Hauwere; -- 15. Decentralized POMDPs / Frans A. Oliehoek; -- 16. Psychological and neuroscientific connections with reinforcement learning / Ashvin Shah; -- 17. Reinforcement learning in games / István Szita; --  18. Reinforcement learning in robotics: a survey / Jens Kober, Jan Peters; -- 19. Conclusions, future directions and outlook / Marco Wiering, Martijn van Otterlo
ER  -