Mathematical foundations of reinforcement learning
Material type:
TextLanguage: English Publication details: China: Jsinghua University Press, 2025Description: xvi, 275pISBN: - 9789819739462
- 006.31 ZHA-M
| Item type | Current library | Home library | Collection | Call number | Materials specified | Status | Date due | Barcode | |
|---|---|---|---|---|---|---|---|---|---|
| Books and Monographs | Central Library, NIT Jalandhar General Stacks | Central Library, NIT Jalandhar | Center for Artificial Intelligence | 006.31 ZHA-M (Browse shelf(Opens below)) | Available | 102891 | |||
| Books and Monographs | Central Library, NIT Jalandhar General Stacks | Central Library, NIT Jalandhar | Center for Artificial Intelligence | 006.31 ZHA-M (Browse shelf(Opens below)) | Available | 102892 |
Front Matter
Pages i-xvi
Basic Concepts
Shiyu Zhao
Pages 1-13
State Values and Bellman Equation
Shiyu Zhao
Pages 15-34
Optimal State Values and Bellman Optimality Equation
Shiyu Zhao
Pages 35-55
Value Iteration and Policy Iteration
Shiyu Zhao
Pages 57-76
Monte Carlo Methods
Shiyu Zhao
Pages 77-99
Stochastic Approximation
Shiyu Zhao
Pages 101-124
Temporal-Difference Methods
Shiyu Zhao
Pages 125-150
Value Function Methods
Shiyu Zhao
Pages 151-189
Policy Gradient Methods
Shiyu Zhao
Pages 191-214
Actor-Critic Methods
Shiyu Zhao
Pages 215-236
Back Matter
Pages 237-275
This book provides a mathematical yet accessible introduction to the fundamental concepts, core challenges, and classic reinforcement learning algorithms. It aims to help readers understand the theoretical foundations of algorithms, providing insights into their design and functionality. Numerous illustrative examples are included throughout. The mathematical content is carefully structured to ensure readability and approachability.
The book is divided into two parts. The first part is on the mathematical foundations of reinforcement learning, covering topics such as the Bellman equation, Bellman optimality equation, and stochastic approximation. The second part explicates reinforcement learning algorithms, including value iteration and policy iteration, Monte Carlo methods, temporal-difference methods, value function methods, policy gradient methods, and actor-critic methods.
With its comprehensive scope, the book will appeal to undergraduate and graduate students, post-doctoral researchers, lecturers, industrial researchers, and anyone interested in reinforcement learning.