Meta-Zeta是一个基于强化学习的五子棋(Gobang)模型，主要用以了解AlphaGo Zero的运行原理的Demo，即神经网络是如何指导MCTS做出决策的，以及如何自我对弈学习。源码+教程
-
Updated
Dec 7, 2022 - Python
#
gomuku
Here are 8 public repositories matching this topic...
Extension of OpenAI Gym that implements multiple two-player zero-sum 2-dimension board games
-
Updated
Sep 11, 2022 - Python
My implementation of AlphaZero for gomoku (Wu Zi Qi, 五子棋); Poorman's AlphaZero
-
Updated
Apr 28, 2018 - Python
Artificial Intelligence with Gomuku
-
Updated
Feb 28, 2018 - Java
-
Updated
Jan 20, 2018 - C++
Gomoku game implementation using custom logics (strategy) and deep learning.
-
Updated
May 2, 2023 - Python
Improve this page
Add a description, image, and links to the gomuku topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the gomuku topic, visit your repo's landing page and select "manage topics."