I have been teaching a course on reinforcement learning at Westlake University for three years. This course aims to provide a mathematical but friendly introduction to the fundamental concepts, basic problems, and classical algorithms in reinforcement learning, which is a core discipline in the areas of artificial intelligence. The topics covered in the course include the Bellman equation, Bellman optimality equation, value iteration/policy iteration algorithms, Monte-Carlo based algorithms, temporal-difference algorithms, function approximation, and policy gradient algorithms. Along with the teaching, I have been writting a book as the lecture notes for my students.

• The PDF of the book and the lecture slides can be found on the GitHub homepage

• The lecture videos can be found at the Bilibili homepage and Youtube homepage

• The introduction to the book can be found at the Zhihu page  

• (update in Nov 2022) My book will be published jointly by Springer Nature and Tsinghua University Press. It will be printed arond the second half of 2023.

We will keep updating the videos and slides. Please stay tuned.