Statistical reinforcement learning modern machine learning approaches
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 deci...
| Main Author: | |
|---|---|
| Format: | eBook |
| Language: | English |
| Published: |
Boca Raton, FL
CRC Press
2015
|
| Series: | Chapman & Hall/CRC machine learning & pattern recognition series
|
| Subjects: | |
| Online Access: | |
| Collection: | O'Reilly - Collection details see MPG.ReNa |
Table of Contents:
- Includes bibliographical references (pages 183-189)
- Part IV: Model-Based Reinforcement LearningChapter 10: Transition Model Estimation; Chapter 11: Dimensionality Reduction for Transition Model Estimation; References
- Cover; Contents; Foreword; Preface; Author; Part I: Introduction; Chapter 1: Introduction to Reinforcement Learning; Part II: Model-Free Policy Iteration; 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; Part III: Model-Free Policy Search; Chapter 7: Direct Policy Search by Gradient Ascent; Chapter 8: Direct Policy Search by Expectation-Maximization; Chapter 9: Policy-Prior Search