Code for Multi-Agent Trust Region Policy Optimization

• Python 3.7.6
• OpenAI baselines-tf2
• My fork of Multi-agent Particle Environments
• TensorFlow 2, version: 2.2.0
• OpenAI Gym, version: 0.11.0

git clone https://github.com/hepengli/matrpo.git

cd matrpo

pip install -e .

All training code is contained within ./matrpo/examples.

If you use this repo in your work, please consider citing the corresponding paper:

@misc{li2020multiagent,
      title={Multi-Agent Trust Region Policy Optimization}, 
      author={Hepeng Li and Haibo He},
      year={2020},
      eprint={2010.07916},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}