Materials for the introductory reinforcement learning course A Glance at Reinforcement Learning. If you like this, Make sure you check out rl-resources, which contains all the literature used in the course and tips on where to go next.
This project is built and maintained by Adam Green - adam.green@adgefficiency.com.
The course is built using reveal.js
. A pdf of the slides is included, or you can locally deploy the presentation using:
brew install node
npm install
npm start
The goals of the course are to:
- introduce you to the concepts, ideas and terminology of reinforcement learning
- become familiar with important literature
- understand the current state of the art
- pass on advice from running reinforcement learning experiments
Course content:
- background statistical concepts
- Markov Decision processes
- value function methods (DQN and it's extensions)
- policy gradient methods
- AlphaGo to AlphaZero
- practical advice for experiments
- current state of the art