junxiaosong AlphaZero_Gomoku issues

junxiaosong / AlphaZero_Gomoku

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

MIT License

3.23k stars 962 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

怎么训练其它棋盘大小的模型

#139 Startshark opened 1 month ago
0
typo: rename mcts_porb to mcts_prob

#138 RealHurrison closed 2 months ago
0
怎么保存固定迭代次数的模型或者怎么看Elo等级分

#137 CreanX opened 3 months ago
0
Update policy_value_net_numpy.py

#136 ya0guang closed 3 months ago
0
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 pursuingz opened 5 months ago
1
Asymmetrical game board can't be trainned 棋盘宽和长不等时，如何训练？

#134 zhannahz opened 9 months ago
0
Keras implementation is not RL

#132 itschenxi opened 1 year ago
0
算法并非自己对战

#131 itschenxi closed 1 year ago
0
关于pytorch训练无法收敛的问题

#130 hxb123622 opened 1 year ago
6
各位训练了多久，能下赢自己？

#129 lvsh2012 opened 1 year ago
0
Added tensorflow V2 model

#128 wangjia184 opened 1 year ago
0
Added support of tensorflow v2

#127 wangjia184 closed 1 year ago
0
Siauhoo

#126 siauhoo opened 2 years ago
0
为什么要在'play_data'中反转输入特征？

#125 Michi-123 opened 2 years ago
0
请问如何使用自己训练的权重

#124 zsqdx opened 2 years ago
0
python GUI + 代码分析

#123 YoujiaZhang opened 2 years ago
0
Add res30 PolicyValueNet and gobang

#122 minkefusiji opened 3 years ago
0
roll out in mcts_pure

#121 yunanyan closed 3 years ago
0
Daoz/add resnet for tf

#120 wangershi closed 3 years ago
0
非常想请教一个问题，希望大佬回复

#119 Lufffya closed 3 years ago
4
请问这个网络是多少*多少的大小

#118 MsvcPytorch opened 3 years ago
1
Disable TensorFlow v2 behavior

#117 elmines opened 3 years ago
0
用Pytorch训练保存模型，在human_play中加载模型报错

#116 bxdxstu opened 3 years ago
2
关于训练中断

#115 racerlucas opened 3 years ago
0
修改了游戏规则后训练中的问题

#114 AnterCreeper closed 3 years ago
0
alpha zero是如何避免在不可行的位置落子的

#113 ZhangXi20181002 opened 3 years ago
2
Differences between model amd model2

#112 lironT74 opened 3 years ago
0
关于训练过程的疑问

#111 dx-feng opened 3 years ago
0
Potential error

#110 Fernadoo opened 4 years ago
1
pytorch是否使用了GPU的问题

#109 Okiii-lh opened 4 years ago
3
mcts_pure.py 中的 get_action() 函数 update_with_move(-1) 是否有误？

#108 honeyshine75 closed 4 years ago
2
增加multiprocess支持

#107 dofish closed 4 years ago
1
Do you have model of 15x15 board?

#106 herogan2017 opened 4 years ago
1
I won the provided model on first try... 试下第一局我就赢了自带的模型...

#105 QmZh opened 4 years ago
0
看完代码觉得这个Implemention有问题，欢迎指正

#104 ylf11235 closed 3 years ago
1
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 ycAngus2415 closed 4 years ago
0
如何用 GPU 得到 self-play 数据呢？

#102 cloxnu opened 4 years ago
0
TensorFlow input_states有些疑问

#101 MaybeChow1991 opened 4 years ago
1
关于CNN卷积核mask的问题

#100 huyp182 closed 4 years ago
0
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 cloxnu closed 4 years ago
1
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 apocalypse-revelation closed 4 years ago
0
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 ToBeIronMan opened 4 years ago
3
Keras训练出来的模型无法加载

#96 LLYYKK opened 4 years ago
1
values are the same for different inputs

#95 yueyilia opened 4 years ago
0
谁有兴趣实现一个开源的“Pluribus”？我可以提供赞助。

#94 xbhuang1994 closed 4 years ago
0
after training the model from scratch with Pytorch, running the human_play.py, RuntimeError: Error(s) in loading state_dict for Net:

#93 redblue1987 opened 4 years ago
2
关于AMD CPU利用率的问题

#92 kouzui98 opened 4 years ago
0
关于策略网络和价值网络

#91 zhang-qiang-github opened 5 years ago
0
ORENIST.data　ModuleNotFoundError: No module named 'numpy.core.multiarray\r'

#90 Go-Tak opened 5 years ago
1
Why the temperature parameter is always 1?

#89 terryzhao127 closed 5 years ago
0