prateekstark/matrix-game

Matrix Game

This is a Pytorch implementation of the Matrix Game, a toy problem for analyzing Multi-Agent Reinforcement Learning.

The agents include Simplified Action Decoder and DeepCFR techniques.

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change. Also, please use Black for formatting the code.

Please make sure to update tests as appropriate.

Reference

@misc{hu2019simplified,
    title={Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning},
    author={Hengyuan Hu and Jakob N Foerster},
    year={2019},
    eprint={1912.02288},
    archivePrefix={arXiv},
    primaryClass={cs.AI}
}