PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
This addresses collaboration inefficiencies in MARL, offering a novel approach to enhance agent coordination, though it appears incremental as it builds on existing mutual information methods.
The paper tackles the problem of sub-optimal collaborative behaviors in Multi-Agent Reinforcement Learning (MARL) by proposing PMIC, a framework that selectively maximizes and minimizes mutual information to improve collaboration, achieving superior performance on MARL benchmarks.
Learning to collaborate is critical in Multi-Agent Reinforcement Learning (MARL). Previous works promote collaboration by maximizing the correlation of agents' behaviors, which is typically characterized by Mutual Information (MI) in different forms. However, we reveal sub-optimal collaborative behaviors also emerge with strong correlations, and simply maximizing the MI can, surprisingly, hinder the learning towards better collaboration. To address this issue, we propose a novel MARL framework, called Progressive Mutual Information Collaboration (PMIC), for more effective MI-driven collaboration. PMIC uses a new collaboration criterion measured by the MI between global states and joint actions. Based on this criterion, the key idea of PMIC is maximizing the MI associated with superior collaborative behaviors and minimizing the MI associated with inferior ones. The two MI objectives play complementary roles by facilitating better collaborations while avoiding falling into sub-optimal ones. Experiments on a wide range of MARL benchmarks show the superior performance of PMIC compared with other algorithms.