1st Edition

Reinforcement Learning and Dynamic Programming Using Function Approximators

    280 Pages 74 B/W Illustrations
    by CRC Press

    From household appliances to applications in robotics, engineered systems involving complex dynamics can only be as effective as the algorithms that control them. While Dynamic Programming (DP) has provided researchers with a way to optimally solve decision and control problems involving complex dynamic systems, its practical value was limited by algorithms that lacked the capacity to scale up to realistic problems.

     However, in recent years, dramatic developments in Reinforcement Learning (RL), the model-free counterpart of DP, changed our understanding of what is possible. Those developments led to the creation of reliable methods that can be applied even when a mathematical model of the system is unavailable, allowing researchers to solve challenging control problems in engineering, as well as in a variety of other disciplines, including economics, medicine, and artificial intelligence.

    Reinforcement Learning and Dynamic Programming Using Function Approximators provides a comprehensive and unparalleled exploration of the field of RL and DP. With a focus on continuous-variable problems, this seminal text details essential developments that have substantially altered the field over the past decade. In its pages, pioneering experts provide a concise introduction to classical RL and DP, followed by an extensive presentation of the state-of-the-art and novel methods in RL and DP with approximation. Combining algorithm development with theoretical guarantees, they elaborate on their work with illustrative examples and insightful comparisons. Three individual chapters are dedicated to representative algorithms from each of the major classes of techniques: value iteration, policy iteration, and policy search. The features and performance of these algorithms are highlighted in extensive experimental studies on a range of control applications.

    The recent development of applications involving complex systems has led to a surge of interest in RL and DP methods and the subsequent need for a quality resource on the subject. For graduate students and others new to the field, this book offers a thorough introduction to both the basics and emerging methods. And for those researchers and practitioners working in the fields of optimal and adaptive control, machine learning, artificial intelligence, and operations research, this resource offers a combination of practical algorithms, theoretical analysis, and comprehensive examples that they will be able to adapt and apply to their own work.

    Access the authors' website at www.dcsc.tudelft.nl/rlbook/ for additional material, including computer code used in the studies and information concerning new developments.

    1 Introduction
    The dynamic programming and reinforcement learning problem
    Approximation in dynamic programming and reinforcement learning
    About this book
    2 An introduction to dynamic programming and reinforcement learning
    Introduction
    Markov decision processes
    Value iteration
    Policy iteration
    Policy search
    Summary and discussion
    3 Dynamic programming and reinforcement learning in large and continuous
    spaces
    Introduction
    The need for approximation in large and continuous spaces
    Approximation architectures
    Approximate value iteration
    Approximate policy iteration
    Finding value function approximators automatically
    Approximate policy search
    Comparison of approximate value iteration, policy iteration, and policy search
    Summary and discussion
    4 Approximate value iteration with a fuzzy representation
    Introduction
    Fuzzy Q-iteration
    Analysis of fuzzy Q-iteration
    Optimizing the membership functions
    Experimental study
    Summary and discussion
    5 Approximate policy iteration for online learning and continuous-action control
    Introduction
    A recapitulation of least-squares policy iteration
    Online least-squares policy iteration
    Online LSPI with prior knowledge
    LSPI with continuous-action, polynomial approximation
    Experimental study
    Summary and discussion
    6 Approximate policy search with cross-entropy optimization of basis functions
    Introduction
    Cross-entropy optimization
    Cross-entropy policy search
    Experimental study
    Summary and discussion
    Appendix A Extremely randomized trees
    Structure of the approximator
    Building and using a tree
    Appendix B The cross-entropy method
    Rare-event simulation using the cross-entropy method
    Cross-entropy optimization
    Symbols and abbreviations
    Bibliography
    List of algorithms
    Index

    Biography

    Robert Babuska, Lucian Busoniu, and Bart de Schutter are with the Delft University of Technology. Damien Ernst is with the University of Liege.