marlbenchmark / on-policy

This is the official implementation of Multi-Agent PPO (MAPPO).
https://sites.google.com/view/mappo
MIT License
1.27k stars 292 forks source link

terminal error-render_mpe.sh #67

Closed EddyJason closed 1 year ago

EddyJason commented 1 year ago

I met the troble with the terminal. I can run the train_mpe.py, but I can not run the render_mpe.sh. The terminla proposed the error: env is MPE Traceback (most recent call last): File "render/render_mpe.py", line 12, in from onpolicy.config import get_config ModuleNotFoundError: No module named 'onpolicy' But the module is not wrong.

HosnLS commented 1 year ago

Please double check that you are following the installation guide, in proper virtual environment (if using conda) and pay attention to shell terminal version, for example, sometimes git on Windows and tmux on Linux may have problems.

XHN-1 commented 1 year ago

Reinstall the onpolicy package

cd on-policy
pip install -e .

And check pip list

chatsmile commented 9 months ago

我运行render_mpe.sh时遇到了问题,报错如下 No such file or directory: 'xxx/actor_agent0.pt' 我不知道如何修正。

ycslnc commented 7 months ago

你好,我也遇到了这个问题,请问你解决了吗?

chatsmile commented 7 months ago

这是来自QQ邮箱的假期自动回复邮件。   您好,我最近正在休假中,无法亲自回复您的邮件。我将在假期结束后,尽快给您回复。