YoujiaZhang / AlphaGo-Zero-Gobang
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
☆86Updated 2 years ago
Alternatives and similar repositories for AlphaGo-Zero-Gobang:
Users that are interested in AlphaGo-Zero-Gobang are comparing it to the libraries listed below
- 使用alphazero算法打造属于你自己的象棋AI☆241Updated 2 years ago
- 本项目主要是采用蒙特卡洛搜索树与残差神经网络实现的一个可在小规模硬 件设施上短期训练一个拥有较强棋力的五子棋 AI。参考 AlphaGo Zero 原始论文 《Mastering the game of Go without human knowledge》实现的一个在五子…☆38Updated 2 years ago
- An asynchronous/parallel method of AlphaGo Zero algorithm with Gomoku☆197Updated this week
- ☆60Updated 6 years ago
- A pytorch based Gomoku game model. Alpha Zero algorithm based reinforcement Learning and Monte Carlo Tree Search model.☆163Updated 5 years ago
- 基于Pytorch, 使用强化学习(自博弈+MCTS)训练一个五子棋AI☆23Updated 3 years ago
- AlphaZero implemented Chinese chess. AlphaGo Zero / AlphaZero实践项目，实现中国象棋。☆497Updated last year
- A tiny re-implementation of AlphaGo Zero (in Gomoku)☆73Updated 6 years ago
- ♟♟♟♟♟ A Gomoku game AI based on Monte Carlo Tree Search, can be trained on policy-value network now. 一个蒙特卡洛树搜索算法实现的五子棋 AI，现可用神经网络训练模型。☆44Updated 4 years ago
- A relatively strong gomoku AI☆87Updated 2 years ago
- A gobang robot based on reinforcement learning.☆135Updated last year
- 基于miniGo的幻影围棋AI，2019中国计算机博弈大赛幻影围棋组冠军；AI of Phantom Go based on miniGo☆48Updated last year
- 人工智能大作业项目:五子棋游戏 Artificial intelligence assignment project: Gobang Game☆45Updated 4 years ago
- 使用Python制作的五子棋游戏☆136Updated 7 months ago
- MNIST·扩展数据集·手写识别计算器·多目标检测·可解释性分析·可视化·handwriting recognition calculator·multi-target detection·explainability·extended dataset☆20Updated 3 years ago
- Switch to new repo https://github.com/hzyhhzy/KataGomo☆189Updated last week
- 不围棋AI☆26Updated 2 years ago
- 机巧围棋(CleverGo)基于Python+Pygame+PaddlePaddle打造一款点击按钮就能可视化地训练围棋人工智能的程序。☆70Updated 3 years ago
- 基于DQN的五子棋人机对弈☆57Updated 5 years ago
- 用深度学习+强化学习编写的一个五子棋人工智障☆39Updated 7 years ago
- ☆19Updated 2 years ago
- 围棋 AI，仿照 AlphaGo☆12Updated 2 years ago
- Using deep reinforcement learning to play Snake game(贪吃蛇).☆79Updated 3 years ago
- Chinese Chess AI game client☆27Updated 7 years ago
- This work attempts to train AlphaZero agents on the game of Chain Reaction☆23Updated 2 years ago
- Implement AlphaZero/AlphaGo Zero methods on Chinese chess.☆1,117Updated last year
- 最基本的基于蒙特卡洛搜索树(MCTS)的五子棋。☆12Updated 3 years ago
- A strong gomoku/renju playing engine supporting Gomocup protocol.☆20Updated 2 years ago
- 中国象棋alpha zero程序☆393Updated 6 years ago
- Gobang MCTS ：蒙特卡洛搜索树使用C++实现五子棋AI算法 ——同济大学☆10Updated last year