-
Notifications
You must be signed in to change notification settings - Fork 46
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
how can i use benchmarl run my own environment? #145
Comments
Thanks for this. So first it should be compatible with torchrl. Then you need to create a new task https://github.com/facebookresearch/BenchMARL/tree/main/examples/extending/task Here is a PR example of following this process and adding a new task #84 |
My environment is a mpe environment, like https://github.com/openai/multiagent-particle-envs, so i don't know how to use it on benchmarl, i'll try this https://github.com/facebookresearch/BenchMARL/tree/main/examples/extending/task, thanks |
That's great, we are compatible in many ways with MPE envs! You could use the PettingZoo interface (there are already other MPE envs in benchmal through that). Basically following something like #84 Or you can implement it vectorized using VMAS (https://github.com/proroklab/VectorizedMultiAgentSimulator) which basically is compatible with all MPE features but faster |
I have a new environment, how can i use benchmarl to run it,Thanks
The text was updated successfully, but these errors were encountered: