This project is inspired by RLCard and gym, and aims to provide a Richii-Mahjong AI that is generic enough to be used in any RL environment. Several AI players will be included as pre-trained agents.
This project is still WIP. This page will be soon updated!
Install dependencies by running:
pip install -r requirements.txt
See requirements.txt for more information. The most important dependencies are:
- mahjong - the python utilities for Mahjong.
- Flask - the web server used to make manual actions locally.
This project is currently locked from contribution, as it is still heavily under development.
If you'd like to contribute, feel free to contact my email: da-kun@sjtu.edu.cn.
The code is licensed under the MIT license.
The project kicks off by Team DeepShanties, a group of students from SJTU.
