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
PythonMIT
Stargazers
- aimerhub
- dannis999
- DannyxiuzqBUAA
- Dethanker
- Duanylluestc
- duma-repo北京
- elans2
- goooolooBeijing
- HackYardoNGC 2050
- hcjiAgricultural Genomics Institute at Shenzhen-CAAS
- JackWenx
- JulieJin-km
- KEXT1977
- lixiangweiabc
- methodref
- nyh3174680732Southwest Jiaotong University
- obraveo
- ParallelWorlds1
- Peace-knight
- planegoose
- qiujunhan
- RealHurrison
- SaifLauSouth China University of Technology
- Saigyouji-Youmu
- terenceyjh
- TimZhiX
- Tridagger
- vcccbbhLos Angeles
- Yixuan-2002
- YoujiaZhangHUST
- yuanjialegithubChina
- ZhangYiqun018Northeastern University China
- zrbpkuyp
- zxzxzx217
- zznew
- zzy-xixi