---
title: "MFVFD: A Multi-Agent Q-Learning Approach to Cooperative and Non-Cooperative Tasks"
authors:
  - "Tianhao Zhang"
  - "Qiwei Ye"
  - "Jiang Bian"
  - "Guangming Xie"
  - "Tie-Yan Liu"
doi: "10.24963/ijcai.2021/70"
url: "https://ijcai.org/proceedings/2021/70"
pdf: "https://ijcai.org/proceedings/2021/0070.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "500-506"
track: "Main Track"
keywords:
  - "Agent-based and Multi-agent Systems: Noncooperative Games"
  - "Agent-based and Multi-agent Systems: Multi-agent Learning"
---

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

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

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 500-506. DOI: [10.24963/ijcai.2021/70](https://doi.org/10.24963/ijcai.2021/70)

## 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.