Statistical Reinforcement Learning: Modern Machine Learning Approaches

Reinforcement learning (RL) is a framework for decision making in unknown environments based on a large amount of data. Several practical RL applications for business intelligence, plant control, and game players have been successfully explored in recent years. Providing an accessible introduction to the field, this book covers model-based and model-free approaches, policy iteration, and policy search methods. It presents illustrative examples and state-of-the-art results, including dimensionality reduction in RL and risk-sensitive RLm. The book provides a bridge between RL and data mining and machine learning research.

Table of Contents

Chapter 1 Introduction to Reinforcement Learning
Chapter 2 Policy Iteration with Value Function Approximation
Chapter 3 Basis Design for Value Function Approximation
Chapter 4 Sample Reuse in Policy Iteration
Chapter 5 Active Learning in Policy Iteration
Chapter 6 Robust Policy Iteration
Chapter 7 Direct Policy Search by Gradient Ascent
Chapter 8 Direct Policy Search by Expectation-Maximization
Chapter 9 Policy-Prior Search
Chapter 10 Transition Model Estimation
Chapter 11 Dimensionality Reduction for Transition Model Estimation