Awesome

CFCQL

Code for NeurIPS2023 accepted paper: Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning.

For running code in discrete action space, see "README.md" in "discrete" directory. For running code in continuous action space, see "README.md" in "continuous" directory.

Please consider citing:

@inproceedings{
    shao2023counterfactual,
    title={Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning},
    author={Jianzhun Shao and Yun Qu and Chen Chen and Hongchang Zhang and Xiangyang Ji},
    booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
    year={2023},
    url={https://openreview.net/forum?id=62zmO4mv8X}
}