A generic implementation of AlphaZero in Python that supports multiplayer games.
I will be using this project to explore training agents for multiplayer games through self-play.
Based on the AlphaGo Zero method described here:
Silver, D. et al. Mastering the game of Go without Human Knowledge. Nature 550, 354-359 (2017).
https://deepmind.com/research/publications/mastering-game-go-without-human-knowledge/