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

Tianhao Zhang, Qiwei Ye, Jiang Bian, Guangming Xie, Tie-Yan Liu

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.
BibTeX
@inproceedings{zhang2021mfvfd,
  author = {Tianhao Zhang and Qiwei Ye and Jiang Bian and Guangming Xie and Tie-Yan Liu},
  title = {{MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks}},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year = {2021},
  doi = {10.24963/ijcai.2021/70},
}
Figure