Towards Understanding Cooperative Multi-Agent Q-Learning with Value Factorization
This work addresses a theoretical gap for researchers in multi-agent reinforcement learning, though it is incremental as it builds on existing factorization methods.
The paper tackles the limited theoretical understanding of value factorization in cooperative multi-agent Q-learning by formalizing a framework for analysis, revealing that linear factorization enables counterfactual credit assignment but may not converge, and empirically validating these findings on StarCraft II tasks.
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.