Alpha Zero Gobang https://github.com/lihongxun945/alpha-zero-gobang
更早的项目AlphaZero_Gomoku https://github.com/junxiaosong/AlphaZero_Gomoku

PS：另一个五子棋的实现 https://github.com/lihongxun945/gobang

AlphaZero_Gomoku原项目使用的Theano过时（最高支持python 3.9），给模型训练带来一些麻烦。pytorch训练的模型并不能直接被正确地加载在该项目的游戏部分。
一个类似的clone https://github.com/Yoda-wu/alpha_zero_feat/tree/main
经过测试可用的clone https://github.com/gingkg/AlphaZero_Gomoku_PyTorch

本人略微修改ui的clone，基于AlphaZero_Gomoku_PyTorch
https://github.com/Farbitrarily/Gonoku

  1. 自定义了UI界面，修复了Pygame中部分逻辑缺陷。

  2. 改用cpu进行训练，实测训练速度和使用colab的Tesla_T4速度相近，大概两分钟一代。

  3. 15*15棋盘实际训练进度较慢，引用junxiaosong的Tips for training:

    It is good to start with a 6 * 6 board and 4 in a row. For this case, we may obtain a reasonably good model within 500~1000 self-play games in about 2 hours.

    For the case of 8 * 8 board and 5 in a row, it may need 2000~3000 self-play games to get a good model, and it may take about 2 days on a single PC.