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
• ISBN: 1439821089; 9781439821084
• DOI: 10.1201/9781439821091

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 continuous-variable problems, this unparalleled work provides an introduction to classical RL and DP, followed by a presentation of current methods in RL and DP with approximation. Combining algorithm development with theoretical guarantees, it offers illustrative examples that readers will be able to adapt to their own work.