MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks

Abstract

Value function decomposition (VFD) methods under the popular paradigm of centralized training and decentralized execution (CTDE) have promoted multi-agent reinforcement learning progress. However, existing VFD methods proceed from a group's value function decomposition to only solve cooperative tasks. With the individual value function decomposition, we propose MFVFD, a novel multi-agent Q-learning approach for solving cooperative and non-cooperative tasks based on mean-field theory. Our analysis on the Hawk-Dove and Nonmonotonic Cooperation matrix games evaluate MFVFD's convergent solution. Empirical studies on the challenging mixed cooperative-competitive tasks where hundreds of agents coexist demonstrate that MFVFD significantly outperforms existing baselines.

Cite

Text

Zhang et al. "MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/70

Markdown

[Zhang et al. "MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/zhang2021ijcai-mfvfd/) doi:10.24963/IJCAI.2021/70

BibTeX

@inproceedings{zhang2021ijcai-mfvfd,
  title     = {{MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks}},
  author    = {Zhang, Tianhao and Ye, Qiwei and Bian, Jiang and Xie, Guangming and Liu, Tie-Yan},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {500-506},
  doi       = {10.24963/IJCAI.2021/70},
  url       = {https://mlanthology.org/ijcai/2021/zhang2021ijcai-mfvfd/}
}