search

Zeta36 / chess-alpha-zero

Chess reinforcement learning by AlphaGo Zero methods.
MIT License
2.13k stars 481 forks source link

Made changes to model_chess.py to make self play work #80

Closed crawftv closed 5 years ago

crawftv commented 5 years ago

I made 1 repeated change to the model_chess.py BatchNormalization(axis=-1...). This was to get around an error with tensor shape.

Zeta36 commented 5 years ago

Sorry for the delay