CoGrid is a library for creating multi-agent grid-world environments for reinforcement learning research. It features a functional array-based simulation core, pluggable components (rewards, features, objects), and dual NumPy/JAX backend support.
CoGrid utilizes the parallel PettingZoo API to standardize the multi-agent environment interface. The JAX API is similar to that of JaxMARL.
CoGrid is designed to offer an approachable API for environment customization, compatibility with standard tooling, and pre-build benchmark environments. Full documentation is available at cogrid.readthedocs.io.
Installation
Install from PyPI:
uv add cogrid # or: pip install cogrid
To install with JAX backend support:
uv add "cogrid[jax]" # or: pip install cogrid[jax]
For development, clone the repo and see CONTRIBUTING.md --
uv sync --extra dev installs the package in editable mode with test, lint,
and docs tools.
[!IMPORTANT] CoGrid has gone through a major overhaul and the API has changed significantly. If you need the previous version, you can install it with
pip install cogrid==0.0.16.
Citation
If you use CoGrid in your research, please cite the following paper:
@article{mcdonald2026cogrid,
title={CoGrid \& the Multi-User Gymnasium: A Framework for Multi-Agent Experimentation},
author={McDonald, Chase and Gonzalez, Cleotilde},
journal={arXiv preprint arXiv:2604.15044},
year={2026}
}
Acknowledgements
This work builds on the invaluable efforts of many others:
@article{carroll2019utility,
title={On the utility of learning about humans for human-ai coordination},
author={Carroll, Micah and Shah, Rohin and Ho, Mark K and Griffiths, Tom and Seshia, Sanjit and Abbeel, Pieter and Dragan, Anca},
journal={Advances in neural information processing systems},
volume={32},
year={2019}
}
@article{rutherford2024jaxmarl,
title={Jaxmarl: Multi-agent rl environments and algorithms in jax},
author={Rutherford, Alexander and Ellis, Benjamin and Gallici, Matteo and Cook, Jonathan and Lupu, Andrei and Ingvarsson, Gar{\dh}ar and Willi, Timon and Hammond, Ravi and Khan, Akbir and de Witt, Christian S and others},
journal={Advances in Neural Information Processing Systems},
volume={37},
pages={50925--50951},
year={2024}
}
@article{gessler2025overcookedv2,
title={Overcookedv2: Rethinking overcooked for zero-shot coordination},
author={Gessler, Tobias and Dizdarevic, Tin and Calinescu, Ani and Ellis, Benjamin and Lupu, Andrei and Foerster, Jakob Nicolaus},
journal={arXiv preprint arXiv:2503.17821},
year={2025}
}
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file cogrid-0.3.2.tar.gz.
File metadata
- Download URL: cogrid-0.3.2.tar.gz
- Upload date:
- Size: 189.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
uv/0.10.9 {"installer":{"name":"uv","version":"0.10.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"22.04","id":"jammy","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ef63ac4752098b44e2d0c8ef0f82619c1081081eb9eab4cd047307d763221d2b
|
|
| MD5 |
fdb58561ef40a8035144419634c89ffd
|
|
| BLAKE2b-256 |
5ca3b3e74f3d76b05a48dec282cdf8cf67a61f6a27c4bddd930500ffb5921d9a
|
File details
Details for the file cogrid-0.3.2-py3-none-any.whl.
File metadata
- Download URL: cogrid-0.3.2-py3-none-any.whl
- Upload date:
- Size: 218.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
uv/0.10.9 {"installer":{"name":"uv","version":"0.10.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"22.04","id":"jammy","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fc43aac106b58cd07e26c00db7f5b9f13f27e840dd6cec163adb8a07692927f0
|
|
| MD5 |
3c0c44e13e18fb61068f76c84045eb8c
|
|
| BLAKE2b-256 |
5d69767a3906a59b5cd557316bd9e288938f1ff4c5905e79f9ad80f79418a173
|
