GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → KelvinKarRoy → KKAlphaGoZero

KelvinKarRoy / KKAlphaGoZero

Licence: other
alphaGoZero论文的实现

Programming Languages

python
139335 projects - #7 most used programming language

Labels

alphago-zero

Projects that are alternatives of or similar to KKAlphaGoZero

Alphazero gomoku
An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
Stars: ✭ 2,570 (+7242.86%)
Mutual labels:  alphago-zero
Alpha Zero General
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
Stars: ✭ 2,617 (+7377.14%)
Mutual labels:  alphago-zero
Chess Alpha Zero
Chess reinforcement learning by AlphaGo Zero methods.
Stars: ✭ 1,868 (+5237.14%)
Mutual labels:  alphago-zero
Elf
ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation
Stars: ✭ 3,240 (+9157.14%)
Mutual labels:  alphago-zero
alpha-zero
AlphaZero implementation for Othello, Connect-Four and Tic-Tac-Toe based on "Mastering the game of Go without human knowledge" and "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm" by DeepMind.
Stars: ✭ 68 (+94.29%)
Mutual labels:  alphago-zero
connect4-alpha-zero
Connect4 reinforcement learning by AlphaGo Zero methods.
Stars: ✭ 102 (+191.43%)
Mutual labels:  alphago-zero
sai
SAI: a fork of Leela Zero with variable komi.
Stars: ✭ 92 (+162.86%)
Mutual labels:  alphago-zero
saltzero
Machine learning bot for ultimate tic-tac-toe based on DeepMind's AlphaGo Zero paper. C++ and Python.
Stars: ✭ 27 (-22.86%)
Mutual labels:  alphago-zero
connect4
Solving board games like Connect4 using Deep Reinforcement Learning
Stars: ✭ 33 (-5.71%)
Mutual labels:  alphago-zero
alphaFive
alphaGo版本的五子棋(gobang, gomoku)
Stars: ✭ 51 (+45.71%)
Mutual labels:  alphago-zero
alphazero
Board Game Reinforcement Learning using AlphaZero method. including Makhos (Thai Checkers), Reversi, Connect Four, Tic-tac-toe game rules
Stars: ✭ 24 (-31.43%)
Mutual labels:  alphago-zero
MyAlphaGoZeroOnConnect4
My Simple Implementation of AlphaGo Zero on Connect4
Stars: ✭ 16 (-54.29%)
Mutual labels:  alphago-zero

KKAlphaGoZero

2017年10月nature论文实现 基于TensorFlow
开工日期 2017年12月19日   写的很慢，忙考试，不定期更新  

项目结构

  • rule.py ---------- rule父类

  • utils.py --------- 通用工具类

  • go 围棋相关类  

    • playGo.py -------- 围棋规则类  
    • showGo.py -------- 提供可视化  
    • testGo.py -------- 相关测试

  • gobang 五子棋相关类

    • gobang.py -------- 五子棋规则类

  • model 网络结构类  

    • resnet_model.py --------------- resNet的TensorFlow版本  
    • alphago_zero_resnet_model.py -- alphaGo zero的model
         * test_model.py ----------------- model的测试

  • mcts 蒙特卡洛搜索树类

    • mcts.py --------------- 蒙特卡洛搜索树
    • node.py --------------- 树的节点  
    • edge.py --------------- 树的边  

  • img 项目相关图片

    • net_model.jpg ------ AlphaGo Zero的结构图

任务清单

  • 围棋规则类（可以下）
  • 可视化类
  • resNet网络结构类（正向传播）
  • MCTS
  • 自对弈
  • 增强学习

网络结构

网络结构  

参考资料

AlphaGo

MCTS

更新日志

2018年1月14日

 拖更十天后重启，完善了mcts部分，特别是增加了狄利克雷噪音，使得和论文一致。

2018年1月4日

 准备考试加上元旦休息了一阵，修改了围棋相关类的结构；mcts大体上实现。

2017年12月24日

 基本上完成了mcts相关类的结构设计。

2017年12月23日

 AlphaGo Zero的model写完了！忙网络的实验忙了一下午也没做完，做这个调节一下心情。

2017年12月22日

 对model类注释完毕，并针对此项目进行了部分修改，主要是参数部分。

2017年12月21日

 完善了围棋相关类，增加了结算子目和判断真眼的功能；对围棋类增加了针对AlphaGo Zero输入的格式化；对model类增加了注释。

2017年12月19日

 花了一个下午，完成PlayGo和ShowGo的编写，即对围棋规则类编写完成，并提供最简单的可视化，其后依据后续需要完善其功能。

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].