RODE: Learning Roles To Decompose Multi-agent Tasks

Abstract

Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. However, it is largely unclear how to efficiently discover such a set of roles. To solve this problem, we propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. Learning a role selector based on action effects makes role discovery much easier because it forms a bi-level learning hierarchy -- the role selector searches in a smaller role space and at a lower temporal resolution, while role policies learn in significantly reduced primitive action-observation spaces. We further integrate information about action effects into the role policies to boost learning efficiency and policy generalization. By virtue of these advances, our method (1) outperforms the current state-of-the-art MARL algorithms on 10 of the 14 scenarios that comprise the challenging StarCr

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2020rode

Related papers

• Attention-guided Contrastive Role Representations For Multi-agent Reinforcement Learning (2023)3.64
• Role Play: Learning Adaptive Role-specific Strategies In Multi-agent Interactions (2024)0.00
• ALMA: Hierarchical Learning For Composite Multi-agent Tasks (2022)0.00
• Policy Diagnosis Via Measuring Role Diversity In Cooperative Multi-agent RL (2022)0.00
• Learning Complex Teamwork Tasks Using A Given Sub-task Decomposition (2023)0.00
• Deep Decentralized Multi-task Multi-agent Reinforcement Learning Under Partial Observability (2017)0.00
• An Organizationally-oriented Approach To Enhancing Explainability And Control In Multi-agent Reinforcement Learning (2025)2.26
• Heterogeneous Multi-agent Reinforcement Learning For Zero-shot Scalable Collaboration (2024)6.34