diff --git a/README.md b/README.md index 49eae9c..d1dd7d6 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,9 @@ # 强化学习的数学基础 +![Python](https://img.shields.io/badge/Python-3.10%2B-blue) +![Status](https://img.shields.io/badge/Status-Learning-orange) +![License](https://img.shields.io/badge/License-MIT-green) + 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) @@ -19,11 +23,12 @@ 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。 +- `Lecture slides/`: 课程相关的幻灯片。 +- `Notebooks/`: 包含详细推导和实验过程的 Jupyter Notebooks。 +- `RawBook/`: 原书中的相关资源和代码。 +- `.gitignore`: Git 忽略文件，指定不需要提交到版本控制的文件或目录。 +- `README.md`: 项目说明文档。 +- `LICENSE`: 代码的开源协议说明。 ## 🛠️ 环境配置 diff --git a/1 - Table of contents.pdf b/RawBook/1 - Table of contents.pdf similarity index 100% rename from 1 - Table of contents.pdf rename to RawBook/1 - Table of contents.pdf diff --git a/2 - Overview of this book.pdf b/RawBook/2 - Overview of this book.pdf similarity index 100% rename from 2 - Overview of this book.pdf rename to RawBook/2 - Overview of this book.pdf diff --git a/2 - Preface.pdf b/RawBook/2 - Preface.pdf similarity index 100% rename from 2 - Preface.pdf rename to RawBook/2 - Preface.pdf diff --git a/3 - Chapter 1 Basic Concepts.pdf b/RawBook/3 - Chapter 1 Basic Concepts.pdf similarity index 100% rename from 3 - Chapter 1 Basic Concepts.pdf rename to RawBook/3 - Chapter 1 Basic Concepts.pdf diff --git a/3 - Chapter 10 Actor-Critic Methods.pdf b/RawBook/3 - Chapter 10 Actor-Critic Methods.pdf similarity index 100% rename from 3 - Chapter 10 Actor-Critic Methods.pdf rename to RawBook/3 - Chapter 10 Actor-Critic Methods.pdf diff --git a/3 - Chapter 2 State Values and Bellman Equation.pdf b/RawBook/3 - Chapter 2 State Values and Bellman Equation.pdf similarity index 100% rename from 3 - Chapter 2 State Values and Bellman Equation.pdf rename to RawBook/3 - Chapter 2 State Values and Bellman Equation.pdf diff --git a/3 - Chapter 3 Optimal State Values and Bellman Optimality Equation.pdf b/RawBook/3 - Chapter 3 Optimal State Values and Bellman Optimality Equation.pdf similarity index 100% rename from 3 - Chapter 3 Optimal State Values and Bellman Optimality Equation.pdf rename to RawBook/3 - Chapter 3 Optimal State Values and Bellman Optimality Equation.pdf diff --git a/3 - Chapter 4 Value Iteration and Policy Iteration.pdf b/RawBook/3 - Chapter 4 Value Iteration and Policy Iteration.pdf similarity index 100% rename from 3 - Chapter 4 Value Iteration and Policy Iteration.pdf rename to RawBook/3 - Chapter 4 Value Iteration and Policy Iteration.pdf diff --git a/3 - Chapter 5 Monte Carlo Methods.pdf b/RawBook/3 - Chapter 5 Monte Carlo Methods.pdf similarity index 100% rename from 3 - Chapter 5 Monte Carlo Methods.pdf rename to RawBook/3 - Chapter 5 Monte Carlo Methods.pdf diff --git a/3 - Chapter 6 Stochastic Approximation.pdf b/RawBook/3 - Chapter 6 Stochastic Approximation.pdf similarity index 100% rename from 3 - Chapter 6 Stochastic Approximation.pdf rename to RawBook/3 - Chapter 6 Stochastic Approximation.pdf diff --git a/3 - Chapter 7 Temporal-Difference Methods.pdf b/RawBook/3 - Chapter 7 Temporal-Difference Methods.pdf similarity index 100% rename from 3 - Chapter 7 Temporal-Difference Methods.pdf rename to RawBook/3 - Chapter 7 Temporal-Difference Methods.pdf diff --git a/3 - Chapter 8 Value Function Methods.pdf b/RawBook/3 - Chapter 8 Value Function Methods.pdf similarity index 100% rename from 3 - Chapter 8 Value Function Methods.pdf rename to RawBook/3 - Chapter 8 Value Function Methods.pdf diff --git a/3 - Chapter 9 Policy Gradient Methods.pdf b/RawBook/3 - Chapter 9 Policy Gradient Methods.pdf similarity index 100% rename from 3 - Chapter 9 Policy Gradient Methods.pdf rename to RawBook/3 - Chapter 9 Policy Gradient Methods.pdf diff --git a/4 - Appendix.pdf b/RawBook/4 - Appendix.pdf similarity index 100% rename from 4 - Appendix.pdf rename to RawBook/4 - Appendix.pdf diff --git a/5 - Errata for the Springer version.pdf b/RawBook/5 - Errata for the Springer version.pdf similarity index 100% rename from 5 - Errata for the Springer version.pdf rename to RawBook/5 - Errata for the Springer version.pdf diff --git a/Book-all-in-one.pdf b/RawBook/Book-all-in-one.pdf similarity index 100% rename from Book-all-in-one.pdf rename to RawBook/Book-all-in-one.pdf diff --git a/Readme_Images/BookCoverChinese.png b/Readme_Images/BookCoverChinese.png deleted file mode 100644 index 932f912..0000000 Binary files a/Readme_Images/BookCoverChinese.png and /dev/null differ diff --git a/Readme_Images/BookCoverSpringer.png b/Readme_Images/BookCoverSpringer.png deleted file mode 100644 index 63a5345..0000000 Binary files a/Readme_Images/BookCoverSpringer.png and /dev/null differ diff --git a/Readme_Images/BookMap.png b/Readme_Images/BookMap.png deleted file mode 100644 index 48a1065..0000000 Binary files a/Readme_Images/BookMap.png and /dev/null differ diff --git a/Readme_Images/EnglishLectureVideo.png b/Readme_Images/EnglishLectureVideo.png deleted file mode 100644 index becc9ef..0000000 Binary files a/Readme_Images/EnglishLectureVideo.png and /dev/null differ diff --git a/Readme_Images/review1.jpg b/Readme_Images/review1.jpg deleted file mode 100644 index 21392a3..0000000 Binary files a/Readme_Images/review1.jpg and /dev/null differ diff --git a/Readme_Images/review2.jpg b/Readme_Images/review2.jpg deleted file mode 100644 index 701dfb8..0000000 Binary files a/Readme_Images/review2.jpg and /dev/null differ