Learning Bilateral Team Formation in Cooperative Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a framework for learning bilateral team formation in dynamic multi-agent systems, addressing a gap in existing research by focusing on two-sided groupings and their impact on policy performance and generalization.

Contribution

It presents a novel approach to bilateral team formation in MARL, exploring how algorithmic properties affect outcomes in dynamic populations.

Findings

Achieves competitive performance in multi-agent scenarios

Demonstrates improved generalization over existing methods

Provides insights into algorithmic influences on team formation

Abstract

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.