mlsanityData to 7 Oct 2026

Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning

arXiv 2404.10976 ↗First posted 17 Apr 2024cs.LG cs.AI cs.MAcited by 17

Not on the map. Why?

Abstract (arXiv)

Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations, neglecting higher-order relationships. While several approaches attempt to extend cooperation modelling to encompass behaviour similarities within groups, they commonly fall short in concurrently learning the latent graph, thereby constraining the information exchange among partially observed agents. To overcome these limitations, we present a novel approach to infer the Group-Aware Coordination Graph (GACG), which is designed to capture both the cooperation between agent pairs based on current observations and group-level dependencies from behaviour patterns observed across trajectories. This graph is further used in graph convolution for information exchange between agents during decision-making. To further ensure behavioural consistency among agents within the same group, we introduce a group distance loss, which promotes group cohesion and encourages specialization between groups. Our evaluations, conducted on StarCraft II micromanagement tasks, demonstrate GACG's superior performance. An ablation study further provides experimental evidence of the effectiveness of each component of our method.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 17 Apr 2024.

Builds on

20 of 37 references.

References · 20

  1. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  2. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  3. 2019The StarCraft Multi-Agent Challengecited by 589
  4. 2018Graph Convolutional Reinforcement Learningcited by 148
  5. 2020ROMA: Multi-Agent Reinforcement Learning with Emergent Rolescited by 135
  6. 2019Deep Coordination Graphscited by 96
  7. 2019Learning Nearly Decomposable Value Functions Via Communication Minimizationcited by 85
  8. 2019Multi-Agent Game Abstraction via Graph Attention Neural Networkcited by 81
  9. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 58
  10. 2018Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networkscited by 54
  11. 2019PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learningcited by 46
  12. 2020Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learningcited by 38
8 more
  1. 2019Learning to Score Behaviors for Guided Policy Optimizationcited by 34
  2. 2021Context-Aware Sparse Deep Coordination Graphscited by 27
  3. 2018Relational Forward Models for Multi-Agent Learningcited by 21
  4. 2021Self-Organized Polynomial-Time Coordination Graphscited by 14
  5. 2022Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samplescited by 10
  6. 2022Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processescited by 7
  7. 2024Layer-diverse Negative Sampling for Graph Neural Networkscited by 7
  8. 2024Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 8.

17 papers.

Sort:

By area:

  1. 2025Agentic AI Security: Threats, Defenses, Evaluation, and Open Challengescited by 26
  2. 2025Seven Security Challenges in Cross-domain Multi-agent LLM Systemscited by 12
  3. 2025Deep Meta Coordination Graphs for Multi-agent Reinforcement Learningcited by 6
  4. 2025Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learningcited by 2
  5. 2026Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learningcited by 2
  6. 2024HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learningcited by 1
  7. 2025Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learningcited by 1
  8. 2026PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documentscited by 1
  9. 2025CTC: The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learningcited by 0
  10. 2025Bi-level Mean Field: Dynamic Grouping for Large-Scale MARLcited by 0
  11. 2025Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learningcited by 0
  12. 2026Do LLM-derived graph priors improve multi-agent coordination?cited by 0
5 more
  1. 2026A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communicationcited by 0
  2. 2026SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learningcited by 0
  3. 2026Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learningcited by 0
  4. 2026Coordination Graphs for Constrained Multi-Agent Reinforcement Learningcited by 0
  5. 2026Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networkscited by 0