Hello everyone! 👋 🤗, so basically, the goal of this repo is to act as a learning companion as you go through the standard RL text: Reinforcement Learning: An Introduction (2nd Edition)
All code is written in Javascript and uses environments from an OpenAI gym like library written just for this Repo.(see, 📂 Environments ) for function approximators we used tensorflow.js
🗒: Note that this project is meant to be used for learning and researching purposes only and it is not meant to be used for production.
- Policy Iteration
- Sarsa (On-policy)
- Q-Learning (Off-policy)
- Monte-Carlo
Install all dependencies
npm install
Build the project
npm run build
Run all the tests
npm test