# Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2404.10976 · HTML: https://mlsanity.com/paper/2404.10976/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 37 references that are in the map.
- First posted on arXiv 17 Apr 2024.

## Builds on (most cited first, 20 of 20)

- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Graph Convolutional Reinforcement Learning](https://mlsanity.com/paper/1810.09202/) (2018)
- [ROMA: Multi-Agent Reinforcement Learning with Emergent Roles](https://mlsanity.com/paper/2003.08039/) (2020)
- [Deep Coordination Graphs](https://mlsanity.com/paper/1910.00091/) (2019)
- [Learning Nearly Decomposable Value Functions Via Communication Minimization](https://mlsanity.com/paper/1910.05366/) (2019)
- [Multi-Agent Game Abstraction via Graph Attention Neural Network](https://mlsanity.com/paper/1911.10715/) (2019)
- [Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2006.11438/) (2020)
- [Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networks](https://mlsanity.com/paper/1810.10408/) (2018)
- [PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1911.00025/) (2019)
- [Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2006.04222/) (2020)
- [Learning to Score Behaviors for Guided Policy Optimization](https://mlsanity.com/paper/1906.04349/) (2019)
- [Context-Aware Sparse Deep Coordination Graphs](https://mlsanity.com/paper/2106.02886/) (2021)
- [Relational Forward Models for Multi-Agent Learning](https://mlsanity.com/paper/1809.11044/) (2018)
- [Self-Organized Polynomial-Time Coordination Graphs](https://mlsanity.com/paper/2112.03547/) (2021)
- [Learning from the Dark: Boosting Graph Convolutional Neural Networks with Diverse Negative Samples](https://mlsanity.com/paper/2210.00728/) (2022)
- [Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processes](https://mlsanity.com/paper/2212.02055/) (2022)
- [Layer-diverse Negative Sampling for Graph Neural Networks](https://mlsanity.com/paper/2403.11408/) (2024)
- [Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2403.19253/) (2024)

## Built on by (most cited first, 18 of 18)

- [Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges](https://mlsanity.com/paper/2510.23883/) (2025)
- [Seven Security Challenges in Cross-domain Multi-agent LLM Systems](https://mlsanity.com/paper/2505.23847/) (2025)
- [Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2502.04028/) (2025)
- [Bayesian Ego-graph Inference for Networked Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2509.16606/) (2025)
- [Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2507.23604/) (2025)
- [Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2602.17009/) (2026)
- [HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2409.11741/) (2024)
- [SDHN: Skewness-Driven Hypergraph Networks for Enhanced Localized Multi-Robot Coordination](https://mlsanity.com/paper/2504.06684/) (2025)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [CTC: The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2502.00345/) (2025)
- [Bi-level Mean Field: Dynamic Grouping for Large-Scale MARL](https://mlsanity.com/paper/2505.06706/) (2025)
- [Action Dependency Graphs for Globally Optimal Coordinated Reinforcement Learning](https://mlsanity.com/paper/2506.00797/) (2025)
- [Do LLM-derived graph priors improve multi-agent coordination?](https://mlsanity.com/paper/2604.17191/) (2026)
- [A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication](https://mlsanity.com/paper/2604.25972/) (2026)
- [SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.08391/) (2026)
- [Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.17393/) (2026)
- [Coordination Graphs for Constrained Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2606.02337/) (2026)
- [Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks](https://mlsanity.com/paper/2607.09330/) (2026)

## 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.