Metadata-Version: 2.4
Name: magent2
Version: 0.3.4
Summary: Multi-Agent Reinforcement Learning environments with very large numbers of agents.
Author-email: Farama Foundation <contact@farama.org>
License: MIT License
Project-URL: Homepage, https://farama.org
Project-URL: Repository, https://github.com/Farama-Foundation/MAgent2
Project-URL: Documentation, https://magent2.farama.org
Project-URL: Bug Report, https://github.com/Farama-Foundation/MAgent2/issues
Keywords: Reinforcement Learning,game,RL,AI
Classifier: Development Status :: 5 - Production/Stable
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=1.21.0
Requires-Dist: pygame-ce>=2.1.0
Requires-Dist: pettingzoo>=1.23.1
Dynamic: license-file

<p align="center">
    <img src="https://raw.githubusercontent.com/Farama-Foundation/MAgent2/main/MAgent2-text.png" width="500px"/>
</p>

MAgent2 is a library for the creation of environments where large numbers of pixel agents in a gridworld interact in battles or other competitive scenarios.

<p align="center">
  <img src="https://raw.githubusercontent.com/Farama-Foundation/MAgent2/main/docs/environments/adversarial_pursuit.gif" width="200">
</p>

MAgent2 is a maintained fork of the original [MAgent](https://github.com/geek-ai/MAgent) codebase. It contains some [reference environments](https://github.com/Farama-Foundation/MAgent2/tree/main/magent2/environments) implemented using the [PettingZoo](https://github.com/Farama-Foundation/PettingZoo) API. These environments used to be included in PettingZoo itself, but have been moved here to exist independently. They are being regularly maintained and will receive bug fixes, support new versions of Python, etc. Development used to take place at [github.com/Farama-Foundation/MAgent](https://github.com/Farama-Foundation/MAgent) but was moved to [github.com/Farama-Foundation/MAgent2](https://github.com/Farama-Foundation/MAgent2) so that the distinction from the original MAgent library is clear to users.

## Installation
Install using pip: `pip install magent2`. See [docs](https://magent2.farama.org/) for usage information.


## Requirements
MAgent2 supports Linux and macOS and Python 3.8+.

## References
```
@inproceedings{zheng2018magent,
  title={MAgent: A many-agent reinforcement learning platform for artificial collective intelligence},
  author={Zheng, Lianmin and Yang, Jiacheng and Cai, Han and Zhou, Ming and Zhang, Weinan and Wang, Jun and Yu, Yong},
  booktitle={Thirty-Second AAAI Conference on Artificial Intelligence},
  year={2018}
}
```

If you wish to cite this repo with it's modifications specifically, please cite:

```
@misc{magent2020,
  author = {Terry, Jordan K and Black, Benjamin and Jayakumar, Mario},
  title = {MAgent},
  year = {2020},
  publisher = {GitHub},
  note = {GitHub repository},
  howpublished = {\url{https://github.com/Farama-Foundation/MAgent}}
}
```

## Project Maintainers
- Project Manager: [Travis Virgil](https://github.com/virgilt) - `travis@farama.org`
- Maintenance for this project is also contributed by the broader Farama team: [farama.org/team](https://farama.org/team).
