suragnair / alpha-zero-general

A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
MIT License
3.9k stars 1.04k forks source link

Added Ninemensmorris Game #313

Open LittleH0rst opened 11 months ago

LittleH0rst commented 11 months ago

Adds the game "nine mens morris" to the repository. The neural network is the same as in the given othello implementation, there is surely room for improvement. The game has a larger statespace compared to the exisiting games in the repository, the trained model outperforms a random agent, but shows obvious flaws when looking at the end game decisions. I hope this implementation helps, maybe someone wants to improve the given code.