Reinforcement Learning

State-of-the-Art

Editors:

ISBN: 978-3-642-27644-6 (Print) 978-3-642-27645-3 (Online)

Table of contents (19 chapters)

  1. Front Matter

    Pages 1-31

  2. Introductory Part

    1. Front Matter

      Pages 1-1

    2. No Access

      Book Chapter

      Pages 3-42

      Reinforcement Learning and Markov Decision Processes

  3. Efficient Solution Frameworks

    1. Front Matter

      Pages 43-43

    2. No Access

      Book Chapter

      Pages 45-73

      Batch Reinforcement Learning

    3. No Access

      Book Chapter

      Pages 75-109

      Least-Squares Methods for Policy Iteration

    4. No Access

      Book Chapter

      Pages 111-141

      Learning and Using Models

    5. No Access

      Book Chapter

      Pages 143-173

      Transfer in Reinforcement Learning: A Framework and a Survey

    6. No Access

      Book Chapter

      Pages 175-204

      Sample Complexity Bounds of Exploration

  4. Constructive-Representational Directions

    1. Front Matter

      Pages 205-205

    2. No Access

      Book Chapter

      Pages 207-251

      Reinforcement Learning in Continuous State and Action Spaces

    3. No Access

      Book Chapter

      Pages 253-292

      Solving Relational and First-Order Logical Markov Decision Processes: A Survey

    4. No Access

      Book Chapter

      Pages 293-323

      Hierarchical Approaches

    5. No Access

      Book Chapter

      Pages 325-355

      Evolutionary Computation for Reinforcement Learning

  5. Probabilistic Models of Self and Others

    1. Front Matter

      Pages 357-357

    2. No Access

      Book Chapter

      Pages 359-386

      Bayesian Reinforcement Learning

    3. No Access

      Book Chapter

      Pages 387-414

      Partially Observable Markov Decision Processes

    4. No Access

      Book Chapter

      Pages 415-439

      Predictively Defined Representations of State

    5. No Access

      Book Chapter

      Pages 441-470

      Game Theory and Multi-agent Reinforcement Learning

    6. No Access

      Book Chapter

      Pages 471-503

      Decentralized POMDPs

  6. Domains and Background

    1. Front Matter

      Pages 505-505

    2. No Access

      Book Chapter

      Pages 507-537

      Psychological and Neuroscientific Connections with Reinforcement Learning

    3. No Access

      Book Chapter

      Pages 539-577

      Reinforcement Learning in Games

    4. No Access

      Book Chapter

      Pages 579-610

      Reinforcement Learning in Robotics: A Survey

  7. Closing

    1. Front Matter

      Pages 611-611

    2. No Access

      Book Chapter

      Pages 613-630

      Conclusions, Future Directions and Outlook

  8. Back Matter

    Pages 631-638