What it does
Reinforcement learning is a type of AI that learns by trial and error, earning rewards for good choices. This book explains its key ideas and classic methods from a mathematical point of view.
The author aims to show not just how each method works but why. The maths is kept at a manageable level, and every example uses a simple grid-world game. Each of the ten chapters builds on the one before.
It grew from the author's graduate course, and lecture videos are available in Chinese and English. Readers need some knowledge of probability and linear algebra.
Who it's for
University students, researchers and practitioners who want a solid grounding in reinforcement learning.
Can I use it without coding?
Yes. It's a book with lecture videos; nothing to install. New to this? Start here.
Can I run it?
- Runs on
- Web browser
- Computer
- An ordinary computer is fine
- API key
- Not needed
Try it
- Watch the lecture videos, available in English and Chinese on YouTube.
- Read the book's chapters in order, since each one builds on the one before.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- No standard license listed. Check the GitHub page before using it for business.
- More on staying safe
Where people are talking about it
- Mathematical Foundations of Reinforcement LearningHacker News · Mar 2025