Attention-guided Contrastive Role Representations For Multi-agent Reinforcement Learning

Abstract

Real-world multi-agent tasks usually involve dynamic team composition with the emergence of roles, which should also be a key to efficient cooperation in multi-agent reinforcement learning (MARL). Drawing inspiration from the correlation between roles and agent's behavior patterns, we propose a novel framework of **A**ttention-guided **CO**ntrastive **R**ole representation learning for **M**ARL (**ACORM**) to promote behavior heterogeneity, knowledge transfer, and skillful coordination across agents. First, we introduce mutual information maximization to formalize role representation learning, derive a contrastive learning objective, and concisely approximate the distribution of negative pairs. Second, we leverage an attention mechanism to prompt the global state to attend to learned role representations in value decomposition, implicitly guiding agent coordination in a skillful role space to yield more expressive credit assignment. Experiments on challenging StarCraft II micromanageme

Stats

• citations0
• S2 citations—
• github stars65
• HF likes0
• heat score3.64
• arxiv keyhu2023attention

Related papers

• Role Play: Learning Adaptive Role-specific Strategies In Multi-agent Interactions (2024)0.00
• An Organizationally-oriented Approach To Enhancing Explainability And Control In Multi-agent Reinforcement Learning (2025)2.26
• TACTIC: Task-agnostic Contrastive Pre-training For Inter-agent Communication (2025)3.58
• Learning To Coordinate In Multi-agent Systems: A Coordinated Actor-critic Algorithm And Finite-time Guarantees (2021)0.00
• RODE: Learning Roles To Decompose Multi-agent Tasks (2020)0.00
• Multi-agent Continual Coordination Via Progressive Task Contextualization (2023)5.24
• Modeling The Interaction Between Agents In Cooperative Multi-agent Reinforcement Learning (2021)0.00
• Policy Distillation And Value Matching In Multiagent Reinforcement Learning (2019)10.48