Timezone: »

Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization
Jianhao Wang · Zhizhou Ren · Beining Han · Jianing Ye · Chongjie Zhang

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @

Value factorization is a popular and promising approach to scaling up multi-agent reinforcement learning in cooperative settings, which balances the learning scalability and the representational capacity of value functions. However, the theoretical understanding of such methods is limited. In this paper, we formalize a multi-agent fitted Q-iteration framework for analyzing factorized multi-agent Q-learning. Based on this framework, we investigate linear value factorization and reveal that multi-agent Q-learning with this simple decomposition implicitly realizes a powerful counterfactual credit assignment, but may not converge in some settings. Through further analysis, we find that on-policy training or richer joint value function classes can improve its local or global convergence properties, respectively. Finally, to support our theoretical implications in practical realization, we conduct an empirical analysis of state-of-the-art deep multi-agent Q-learning algorithms on didactic examples and a broad set of StarCraft II unit micromanagement tasks.

Author Information

Jianhao Wang (Tsinghua University)
Zhizhou Ren (University of Illinois at Urbana-Champaign)
Beining Han (Tsinghua University)
Jianing Ye (Tsinghua University)
Chongjie Zhang (Tsinghua University)

More from the Same Authors