alpha_sigma
alpha_sigma copied to clipboard
Published
20 hours ago •
pandezhao
pandezhao
A pytorch based Gomoku game model. Alpha Zero algorithm based reinforcement Learning and Monte Carlo Tree Search model.
Results
1
alpha_sigma issues
Sort by
recently updated
recently updated
newest added
[issue.zip](https://github.com/pandezhao/alpha_sigma/files/4248568/issue.zip) 作者，您好。我尝试把pytorch代码改为1.0.1版本，修改了network的部分代码，可是运行之后，模型model_xx根本没有训练（model_200，model_400,model_600文件内容都一样，我print出来看过了，同样都是一串数字“119547037146038801333356”），cross_entropy_loss值也不在正常范围（60~85），请问您运行环境是什么？pytorch0.3.0版本？您能给我提供点解决思路吗？感谢！
