Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

This is the implementation of our paper "Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning" in NeurIPS 2024.

Getting Started

For setting up environment and running experiments, please see the README.md files under corresponding folders.

Acknowledgement

The code is implement based on the following open-source projects:

• HARL
• EPyMARL
• MPE and semitable's fork
• pymarl2 and benellis3's fork

Citing

If you use this code in your research or find it helpful, please consider citing our paper:

@article{li2024kaleidoscope,
  title={Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning},
  author={Li, Xinran and Pan, Ling and Zhang, Jun},
  booktitle={accepted by the Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS)},
  year={2024}
}