Chinese Chess reinforcement learning by AlphaGo Zero methods.
This project is modified from two projects:
- https://github.com/Zeta36/chess-alpha-zero.git
- https://github.com/timebug/harmless.git And I attached their original version as ZIPs in the root folder.
Note: This project is still under construction!! The new-threads branch reconstrusted the original multi-threading logic and increased the performance reliably
- Python 3.6.3
- tensorflow-gpu: 1.3.0
- Keras: 2.0.8
- python-2.7.x
- pygame-1.9.x
cd chess-alpha-zero vim readme.md
cd harmless-master vim README.md