Hongru/RL-Study

T

Hongru bb67a9a56f Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

.gitignore

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

1 - Table of contents.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

2 - Overview of this book.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

2 - Preface.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 1 Basic Concepts.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 2 State Values and Bellman Equation.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 3 Optimal State Values and Bellman Optimality Equation.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 4 Value Iteration and Policy Iteration.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 5 Monte Carlo Methods.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 6 Stochastic Approximation.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 7 Temporal-Difference Methods.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 8 Value Function Methods.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 9 Policy Gradient Methods.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

3 - Chapter 10 Actor-Critic Methods.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

4 - Appendix.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

5 - Errata for the Springer version.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

Book-all-in-one.pdf

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

LICENSE

Initial commit

2026-02-27 18:19:54 +08:00

README.md

Initial commit: Add reinforcement learning study materials and grid world code

2026-02-27 18:22:23 +08:00

README.md

强化学习的数学基础

本项目是我在学习赵世钰老师书籍 《Mathematical Foundations of Reinforcement Learning》 时建立的个人仓库。主要用于记录学习笔记、公式推导，以及使用 Python/Jupyter Notebook 复现书中的算法和 Grid World 示例。

📚 关于原书 (Original Book)

本项目的核心内容基于赵世钰老师的开源书籍，以下是原书的相关信息：

书名: Mathematical Foundations of Reinforcement Learning
作者: Shiyu Zhao (Westlake University)
GitHub 仓库: Book-Mathematical-Foundation-of-Reinforcement-Learning
配套视频:
- Bilibili (中文)
- YouTube (English)

📂 项目结构

本项目主要包含以下内容：

Code for grid world/:
- python_version/: 使用 Python 复现的 Grid World 环境及相关算法。
- matlab_version/: (可选) 原书提供的 Matlab 参考代码。
Lecture slides/: 课程相关的幻灯片或我的注解。
Notebooks/: (计划中) 包含详细推导和实验过程的 Jupyter Notebooks。

🛠️ 环境配置

本项目使用 Python 进行开发。推荐使用 uv 或 conda 管理环境。

# 安装依赖 (示例)
pip install numpy matplotlib jupyter

📝 开源协议 (License)

关于代码

本项目中由本人编写的复现代码遵循 MIT License 开源协议。这意味着你可以自由地使用、修改和分发这些代码，但请保留原作者的版权声明。

关于笔记

项目中的学习笔记内容仅供个人学习交流使用。

🤝 致谢

特别感谢赵世钰老师提供的精彩教材和开源资源，帮助我们深入理解强化学习的数学原理。