This short RL course introduces the basic concepts of reinforcement learning in a nutshell. Slides are made in English and lectures are given by Bolei in Chinese. The course is for personal entertainment only.
The short course is scheduled as follows. Lectures 1-7 will be the foundation, the others will be the advanced topics, which are optional.
| Topic | Resources | |
|---|---|---|
| Lecture 1 | Overview | slide, Youtube(part1, part2), B站(上集, 下集) |
| Lecture 2 | Markov Decision Process | slide, Youtube(part1, part2), B站(上集, 下集) |
| Lecture 3 | Model-free Prediction and Control | slide, Youtube(part1, part2), B站(上集, 下集) |
| Lecture 4 | Value Function Approximation | slide, Youtube(part1, part2), B站(上集, 下集) |
| Lecture 5 | Policy Optimization: Foundation | slide, Youtube(part1, part2), B站(上集, 下集) |
| Lecture 6 | Policy Optimization: State of the art | slide, Youtube(part1, part2), B站(上集, 下集) |
| Lecture 7 | Model-based RL | slide, Youtube, B站 |
| Lecture 8 | Imitation Learning | |
| Lecture 9 | Distributed computing and RL system design | |
| Lecture 10 | Case Study on AlphaGo Series |