Polygames: Improved Zero Learning

Implementing and improving the AlphaZero algorithm
Post Reply
Rémi Coulom
Posts: 126
Joined: Tue Feb 12, 2008 8:31 pm
Contact:

Polygames: Improved Zero Learning

Post by Rémi Coulom » Sun Feb 02, 2020 2:59 pm

github:
https://github.com/facebookincubator/polygames
paper:
https://arxiv.org/abs/2001.09832
abstract:
Since DeepMind's AlphaZero, Zero learning quickly became the state-of-the-art method for many board games. It can be improved using a fully convolutional structure (no fully connected layer). Using such an architecture plus global pooling, we can create bots independent of the board size. The training can be made more robust by keeping track of the best checkpoints during the training and by training against them. Using these features, we release Polygames, our framework for Zero learning, with its library of games and its checkpoints. We won against strong humans at the game of Hex in 19x19, which was often said to be untractable for zero learning; and in Havannah. We also won several first places at the TAAI competitions.

Post Reply