IJCAI 2021poster16 citations

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.

Agent-based and Multi-agent Systems: Multi-agent LearningAgent-based and Multi-agent Systems: Noncooperative Games
BibTeX
@inproceedings{ijcai2021p70,
  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 = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Zhi-Hua Zhou},
  pages     = {500--506},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/70},
  url       = {https://doi.org/10.24963/ijcai.2021/70},
}
MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks · IJCAI 2021