Learning Bilateral Team Formation in Cooperative Multi-Agent Reinforcement Learning
This addresses team formation for multi-agent reinforcement learning, but it is incremental as it builds on existing MARL studies.
The paper tackles the problem of bilateral team formation in dynamic multi-agent systems, introducing a framework that demonstrates competitive performance and improved generalization in most scenarios.
Team formation and the dynamics of team-based learning have drawn significant interest in the context of Multi-Agent Reinforcement Learning (MARL). However, existing studies primarily focus on unilateral groupings, predefined teams, or fixed-population settings, leaving the effects of algorithmic bilateral grouping choices in dynamic populations underexplored. To address this gap, we introduce a framework for learning two-sided team formation in dynamic multi-agent systems. Through this study, we gain insight into what algorithmic properties in bilateral team formation influence policy performance and generalization. We validate our approach using widely adopted multi-agent scenarios, demonstrating competitive performance and improved generalization in most scenarios.