Adding JaxRobotarium, an environment for multi-robot coordination with public sim2real transfer

[shalin-jain]

Hi, firstly, this repo is awesome, I've really enjoyed working within it. Apologies if this isn't the correct way to ask about this, but I am interested in contributing an environment for learning multi-robot coordination on 8 benchmark scenarios that allows for public and free sim-to-real evaluation through the Georgia Tech Robotarium. Specifically, I am hoping to do this by including it as a submodule (an example integration with JaxMARL using this strategy here).

The environment implementation is publicly available here: JaxRobotarium. We report benchmarking results, sim2real experiments, and other implementation details in our arxiv paper. I think this project could be a good fit for JaxMARL and hope to get some guidance on how I could contribute JaxRobotarium to the repo!

[amacrutherford]

Hey! thanks for reaching out and glad the repo has been useful, I'll try make some time to take a look at this over the next week :)

[bsarkar321]

We'd be happy to integrate your JaxRobotarium environment using your submodule strategy! I just have a few suggestions to help us integrate it properly:

1. Move your tests into the upper-level "tests" directory (tests/marbler/test_robotarium_env.py) and convert to the pytest format.
2. Add some common prefix to the start of your new environments in the registration.py (like MARBLER_) so people know that all of them are part of the same domain.
3. Add the recommended training results from the contributing guide
4. Add documentation to docs/Environments as a markdown file (like the existing environments)
   After syncing JaxMARL-Robotarium to our upstream repo, you can submit a pull request, and I can review it from there.