Reinforcement Learning and Dynamic Programming Using Function Approximators

• Main Authors: Busoniu, Lucian, Babuska, Robert, De Schutter, Bart, Ernst, Damien
• Format: eBook Book Web Resource
• Language: English
• Published: Boca Raton CRC Press 2010; Taylor & Francis Group
• Edition: 1
• Series: Automation and control engineering
• Subjects: Computer science; Digital control systems; Dynamic programming; Engineering, computing & technology; Ingénierie, informatique & technologie; Sciences informatiques; Approximate Policy; Policy Search; Parameter Vector; Execution Time; RL Method; Bellman Optimality Equation; Reward Function; Fuzzy Approximator; Inverted Pendulum; Continuous Action Control; Pi; Approximate DP; Bellman Equation; Inverted Pendulum Problem; Policy Improvement Step; DC Motor; Policy Iteration Algorithms; State Action Pair; Stochastic Case; Triangular MFs; Cross-entropy Method; Fuzzy Partition; RL Algorithm; Policy Improvement; Deterministic Case

While Dynamic Programming (DP) has helped solve control problems involving dynamic systems, its value was limited by algorithms that lacked practical scale-up capacity. In recent years, developments in Reinforcement Learning (RL), DP's model-free counterpart, has changed this. Focusing on conti...

Table of Contents:

• Cover -- Title -- Copyright -- Preface -- About the authors -- Contents -- 1 Introduction -- 2 An introduction to dynamic programming and reinforcement learning -- 3 Dynamic programming and reinforcement learning in large and continuous spaces -- 4 Approximate value iteration with a fuzzy representation -- 5 Approximate policy iteration for online learning and continuous-action control -- 6 Approximate policy search with cross-entropy optimization of basis functions -- Appendix A: Extremely randomized trees -- Appendix B: The cross-entropy method -- Symbols and abbreviations -- Bibliography -- List of algorithms -- Index