junxiaosong/AlphaZero_Gomoku
An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)
PythonMIT
Issues
- 0
怎么训练其它棋盘大小的模型
#139 opened by Startshark - 0
怎么保存固定迭代次数的模型或者怎么看Elo等级分
#137 opened by CreanX - 1
模型参数形状与从检查点文件中加载的参数形状不匹配
#135 opened by pursuingz - 2
after training the model from scratch with Pytorch, running the human_play.py, RuntimeError: Error(s) in loading state_dict for Net:
#93 opened by redblue1987 - 0
- 1
Do you have model of 15x15 board?
#106 opened by herogan2017 - 0
Keras implementation is not RL
#132 opened by itschenxi - 0
- 6
关于pytorch训练无法收敛的问题
#130 opened by hxb123622 - 0
各位训练了多久,能下赢自己?
#129 opened by lvsh2012 - 0
为什么要在'play_data'中反转输入特征?
#125 opened by Michi-123 - 0
请问如何使用自己训练的权重
#124 opened by zsqdx - 0
python GUI + 代码分析
#123 opened by YoujiaZhang - 2
用Pytorch训练保存模型,在human_play中加载模型报错
#116 opened by bxdxstu - 1
请问这个网络是多少*多少的大小
#118 opened by MsvcPytorch - 2
- 0
roll out in mcts_pure
#121 opened by yunanyan - 4
非常想请教一个问题,希望大佬回复
#119 opened by Lufffya - 0
关于训练中断
#115 opened by racerlucas - 0
修改了游戏规则后训练中的问题
#114 opened by AnterCreeper - 3
pytorch是否使用了GPU的问题
#109 opened by Okiii-lh - 2
alpha zero是如何避免在不可行的位置落子的
#113 opened by ZhangXi20181002 - 1
Potential error
#110 opened by Fernadoo - 0
Differences between model amd model2
#112 opened by lironT74 - 0
- 1
看完代码觉得这个Implemention有问题,欢迎指正
#104 opened by ylf11235 - 3
大佬,你好,我在用pytorch训练出来的模型,无法加载运行,报了如下错误
#97 opened by ToBeIronMan - 1
- 2
- 0
- 0
关于CNN卷积核mask的问题
#100 opened by huyp182 - 1
大佬您好,我仿照您的代码写了一个 repo,但是训练后总是输给纯蒙特卡洛树 AI
#99 opened by cloxnu - 0
要怎么实现先训练8x8大小的棋局再根据之前的结果训练11x11呢?
#98 opened by apocalypse-revelation - 0
我的是python3,训练误差一致在6左右,降不下去,训练基本无效果
#103 opened by ycAngus2415 - 0
如何用 GPU 得到 self-play 数据呢?
#102 opened by cloxnu - 1
TensorFlow input_states有些疑问
#101 opened by MaybeChow1991 - 1
I win , computer lose,hahaha
#81 opened by AI-liu - 1
Keras训练出来的模型无法加载
#96 opened by LLYYKK - 0
values are the same for different inputs
#95 opened by yueyilia - 3
- 0
谁有兴趣实现一个开源的“Pluribus”?我可以提供赞助。
#94 opened by xbhuang1994 - 0
关于AMD CPU利用率的问题
#92 opened by kouzui98 - 0
关于策略网络和价值网络
#91 opened by zhang-qiang-github - 0
Why the temperature parameter is always 1?
#89 opened by terryzhao127 - 2
使用项目中TensorFlow训练的时候出现memory error怎么解决的啊
#88 opened by liquorxm - 1
- 1
Fail to train policy network
#82 opened by mrmitzh - 4
如何把现在的Net网络改成Resnet网络
#78 opened by liunian321 - 0
- 0
pure MCTS FYI
#79 opened by zhenfelix