Lune

AAAI2026Top-tier venue

GRDC: A Unified Graph-Driven Framework for Role Discovery and Communication in Multi-Agent Reinforcement Learning

Zihong Gao, Hongjian Liang, Yuanhui Hao, Lei Hao, Liangjun Ke

Abstract

Effective coordination in Multi-Agent Reinforcement Learning (MARL) is particularly challenging under partial observability, where agents must identify and coordinate with task-relevant collaborators based solely on local information. Existing methods can be categorised into communicationbased approaches, which allow message exchange but either rigidly predefine or misidentify collaborators, and rolebased approaches, which promote functional specialization based on observed behavioural similarity. However, both paradigms overlook the dynamic and context-specific cooperative dependencies induced by the task, which determine which agents should collaborate, thereby leading to miscommunication or role misassignment under partial observability. We introduce GRDC (Graph-driven Role Discovery and Communication), a unified framework that approximates these dependencies by dynamically constructing local interaction graphs from trajectory embeddings, then uses these graphs to infer roles via prototype matching and to restrict communication to intra-role agents with attention-based aggregation. In addition to role inference and communication, GRDC promotes a structured and compact role space by maximising role entropy, decorrelating prototypes, and dynamically pruning redundant prototypes. Experimental results on Predator Prey, Cooperative Navigation, and SMACv2 demonstrate that GRDC consistently outperforms state-of-the-art communication-and role-based baselines, improving coordination efficiency and training stability across tasks.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on14

  1. Graph Convolutional Reinforcement LearningJiechuan Jiang, Chen Dun, Tiejun Huang, Zongqing LuICLR 2020 · 415 citations
  2. Multi-Agent Game Abstraction via Graph Attention Neural NetworkYong Liu, Weixun Wang, Yujing Hu, Jianye Hao et al.AAAI 2020 · 316 citations
  3. ROMA: Multi-Agent Reinforcement Learning with Emergent RolesTonghan Wang, Heng Dong, Victor R. Lesser, Chongjie ZhangICML 2020 · 286 citations
  4. Balanced Contrastive Learning for Long-Tailed Visual RecognitionJianggang Zhu, Zheng Wang, Jingjing Chen, Yi-Ping Phoebe Chen et al.CVPR 2022 · 194 citations
  5. Learning Nearly Decomposable Value Functions Via Communication MinimizationTonghan Wang, Jianhao Wang, Chongyi Zheng, Chongjie ZhangICLR 2020 · 170 citations

Related papers

  1. R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement LearningHarsh Goel, Mohammad Omama, Behdad Chalaki, Vaishnav Tadiparthi et al.ICML 2025
  2. Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement LearningQian Long, Zihan Zhou, Abhinav Gupta, Fei Fang et al.ICLR 2020
  3. Coordination Between Individual Agents in Multi-Agent Reinforcement LearningYang Zhang, Qingyu Yang, Dou An, Chengwei ZhangAAAI 2021 · 21 citations
  4. Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial ExplorationAndreas Kontogiannis, Konstantinos Papathanasiou, Yi Shen, Giorgos Stamou et al.ICML 2025
  5. Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent SystemsZhuohui Zhang, Bin He, Bin Cheng, Gang LiAAAI 2025 · 10 citations
Dusk over the sea between two cliffs drawn in fine vertical lines