zhoubolei/introRL
Intro to Reinforcement Learning (
| repo name | zhoubolei/introRL |
| repo link | https://github.com/zhoubolei/introRL |
| homepage | |
| language | |
| size (curr.) | 7436 kB |
| stars (curr.) | 634 |
| created | 2020-03-14 |
| license | |
Intro to Reinforcement Learning (强化学习纲要）
Overview
This short course will introduce basic concepts of reinforcement learning in a nutshell. Slides will be made in English and lectures will be given by Bolei in Chinese. The course is for entertainment only.
Course Schedule
The short course will be arranged as follows. Lectures 1-8 will be the foundation, the others will be the advanced topics, which are optional.
| Topic | Resources | |
|---|---|---|
| Lecture 1 | Overview | slide, video1, video2 |
| Lecture 2 | Markov Decision Process | |
| Lecture 3 | Model-free Prediction and Control | |
| Lecture 4 | On-policy and Off-policy Learning | |
| Lecture 5 | Value Function Approximation | |
| Lecture 6 | Policy Optimization: Basics | |
| Lecture 7 | Policy Optimization: State of the art | |
| Lecture 8 | Model-based RL | |
| Lecture 9 | Imitation Learning | |
| Lecture 10 | Distributed computing and RL system design | |
| Lecture 11 | Case Study on AlphaGo Series | |
| Lecture 12 | Case Study on AlphaStar and OpenAI Five | |
| Lecture 13 | Unsupervised Learning | |
| Lecture 14 | Generative Modeling | |
| TBD | … |
