Learning Bilateral Team Formation in Cooperative Multi-Agent Reinforcement Learning

2025/06/24 by Koorosh Moslemi, Moslemi, Koorosh, Chi-Guhn Lee +1
Social Sciences · #Artificial Intelligence (cs.AI) #Computer Science and Game Theory (cs.GT) #Evolutionary Game Theory and Cooperation #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multiagent Systems (cs.MA)

paper · pdf · doi:10.48550/arxiv.2506.20039

openalex publication_date 2025/06/24 · openalex created_date 2025/10/09 · openalex updated_date 2026/07/28

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.

Citations

• Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning
• Field Deployment of Multi-Agent Reinforcement Learning Based Variable Speed Limit Controllers
• Improved Bandits in Many-to-one Matching Markets with Incentive Compatibility
• Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers
• Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition
• The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
• Multi-Agent Collaboration via Reward Attribution Decomposition
• RODE: Learning Roles to Decompose Multi-Agent Tasks
• Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
• Competing Bandits in Matching Markets
• The StarCraft Multi-Agent Challenge
• Multi-Agent Common Knowledge Reinforcement Learning
• QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• Value-Decomposition Networks For Cooperative Multi-Agent Learning
• HyperNetworks
• Stable Matching with Uncertain Linear Preferences
• College Admissions and the Stability of Marriage

Related

• Cooperative and Competitive Biases for Multi-Agent Reinforcement Learning
• Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning
• Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms
• Exploring the Benefits of Teams in Multiagent Learning
• Multi-agent Reinforcement Learning: A Comprehensive Survey