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.

中文翻译：

---

Polygames：改进的零学习

自 DeepMind 的 AlphaZero 以来，零学习迅速成为许多棋盘游戏的最先进方法。可以使用全卷积结构（无全连接层）进行改进。使用这样的架构加上全局池，我们可以创建独立于电路板大小的机器人。通过在训练期间跟踪最佳检查点并针对它们进行训练，可以使训练更加稳健。使用这些功能，我们发布了 Polygames，我们的零学习框架及其游戏库和检查点。我们在 19x19 的 Hex 游戏中战胜了强大的人类，这通常被认为是零学习难以驾驭的；和在哈瓦那。我们还在 TAAI 比赛中多次获得第一名。