📚 DistilRL: A Condensed Introduction

---

[ English | 中文 ]

📚 What This Is

As someone who's been learning reinforcement learning (RL), I've been searching for resources that strike the right balance.

Reinforcement Learning: An Introduction is the bible of RL, but reading it cover-to-cover takes a ton of effort.

That's why I created this tutorial: a streamlined "knowledge vault" to help you absorb the core ideas faster and easier!

---

🎯 Why This Project and how to use (for now)

💡 Key Idea: This tutorial focuses on handpicked chapters from the RL Intro book and blends them with content from a RL Coursera specialization for a smoother learning experience.

🛠️ How to Use: Read the whole tutorial on this site. You will find more details about how this project came to exist and how to best use it in Chapter 0. The Prelude!

---

📋 Catalog

🌟 Introduction

• Chapter 0: Prelude
• Chapter 1: Introduction to RL

🧮 Tabular Solution Methods

Fundamentals of Reinforcement Learning

• Chapter 2: Multi-armed Bandits
• Chapter 3: Markov Decision Process
• Chapter 4: Dynamic Programming

Sample-based Learning Methods

• Chapter 5: Monte Carlo Methods
• Chapter 6: Temporal Difference Learning
• Chapter 7: Planning, Learning, Acting

🤖 Approximate Solution Methods

Value Function Approximation

• Chapter 8: On-policy Prediction with Approximation
• Chapter 9: On-policy Control with Approximation

Policy Approximation

• Chapter 10: Policy Gradient Methods
• Chapter 11: Modern Policy Gradient Methods

---

🤝 Contributing

I welcome contributions to improve this tutorial! Here's how you can help:

• Report Issues: Found a typo or unclear explanation? Open an issue!
• Suggest Improvements: Have ideas for better explanations or new content? Submit a pull request!
• Spread the Word: Share this tutorial with others who might find it useful!
• Translation needed: I am also trying to create a Chinese version of this book somewhen in the future, help me out if you are interested.

---

📜 License

This project is licensed under the MIT License. See the LICENSE file for details.