ABSTRACT

Reinforcement learning is a mathematical framework for developing computer agents that can learn an optimal behavior by relating generic reward signals with its past actions. With numerous successful applications in business intelligence, plant control, and gaming, the RL framework is ideal for decision making in unknown environments with large amo

part 1|2 pages

Part I: Introduction

chapter 1|12 pages

Introduction to Reinforcement Learning

part 2|2 pages

Part II: Model-Free Policy Iteration

chapter 4|18 pages

Sample Reuse in Policy Iteration

chapter 5|14 pages

Active Learning in Policy Iteration

chapter 6|14 pages

Robust Policy Iteration

part 3|2 pages

Part III: Model-Free Policy Search

chapter 7|22 pages

Direct Policy Search by Gradient Ascent

chapter 9|22 pages

Policy-Prior Search

part 4|2 pages

Part IV: Model-Based Reinforcement Learning

chapter 10|16 pages

Transition Model Estimation