Wen-Zhang Liu

Hi, can you tell me which operating system did you use to install xuanpolicy？

You can try to install an MPI program from [here](https://www.microsoft.com/en-us/download/details.aspx?id=57467). Then, reinstall mpi4py： `pip uninstall mpi4py` `pip install mpi4py`

This [link](https://blog.51cto.com/u_14824191/3255805) shows a similar issue to yours, hope it will be useful.

您好，由于玄策近期正在进行版本更新，我们首先在PyTorch版玄策中进行功能更新，因此可能会遇到对TensorFlow或MindSpore不兼容的情况。我们建议您暂时先使用最新版的PyTorch版玄策来学习MARL，在接下来的时间里我们会尽快完成对TensorFlow和MindSpore的兼容。给您造成不变，非常抱歉。如有其它问题，欢迎随时联系！

Hi, you need to use "simple_spread_v3" instead of "simple_spread" for env_id. You can also create a new file named "simple_spread.yaml" and set hyperparameters according to "xuanpolicy/configs/maddpg/mpe/simple_spread_v3.yaml". Then get runner by...

If you want to visualize the model, you can set "render: True" in xuanpolicy/configs/basic.yaml file. After training or testing the model, you can see the videos with tensorboard or wandb...

您好，出现这个错误是因为当前版本没考虑到Windows系统下，magent2环境的动态链接库文件。您可以试着安装一下这个环境，再看是否还会出现该错误？ `pip install magent2` 我们后期会修补这个问题，感谢您的反馈!

Thank you for your kind words and for providing additional information about the simple_speaker_listener scenario of MPE. The simple_speaker_listener scenario in multi-agent particle environments (MPE) involves heterogeneous cooperative agents, which...

Hi, we've noticed that there was an issue with the MARL_OffPolicyBuffer.store() function due to incorrect buffer data shape initialization in the MARL_OffPolicyBuffer.clear() function. Thank you for bringing it to our...

Thank you once again for your valuable advice. We will improve the repo according to your suggestions and comments very soon. As for your question about simple_speaker_listener, simple_world, and simple_reference,...