A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication

Valentin Cuzin-Rambaud; Laetitia Matignon; Maxime Morge

cs.LGApr 28, 2026

A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication

Authors: Valentin Cuzin-Rambaud, Laetitia Matignon, Maxime Morge

Organizations: LIRIS, UCBL · Université Lyon 1, INSA Lyon, CNRS, LIRIS, UMR 5205, Lyon, France

Abstract

In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their actions and converge on their objectives by sharing information. Based on an interaction graph, a subclass of methods employs graph neural networks (GNNs) to learn the communication, enabling agents to improve their internal representations by enriching them with information exchanged. With growing research, we note a lack of explicit structure and framework to distinguish and classify MARL approaches with communication based on GNNs. Thus, this paper surveys recent works in this field. We propose a generalized GNN-based communication process with the goal of making the underlying concepts behind the methods more obvious and accessible.

Explore similar work

HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning
Jun 28, 2026Runze Zhao, Dongruo Zhou, Sumit Kumar Jha +2Multi-Agent Reinforcement Learning Communication
LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning
May 18, 2026Sangjun Bae, Yisak Park, Sanghyeon Lee +1Multi-Agent Reinforcement Learning Communication
SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication
May 26, 2026Mahmoud Abouelyazid, Eman HammadMulti-Agent Reinforcement Learning Multi-Robot Systems

Jun 28, 2026 · cs.AIJ/K move · Enter open · S save

HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning

Runze Zhao, Dongruo Zhou, Sumit Kumar Jha, Nathaniel D. Bastian+1

Cooperative multi-agent reinforcement learning (MARL) often relies on communication to mitigate partial observability, yet most existing protocols treat messages as flat dense vectors detached from the structure of the observations they summarize. This design overlooks an important source of inductive bias in many cooperative environments, where observations naturally follow a hierarchy such as groups and entities. We propose \textsc{HiComm}, a plug-in communication module that grounds messages in the sender's hierarchical observation. \textsc{HiComm} is receiver-driven: the receiver issues a query, and the hierarchy is resolved through a three-stage decoding process that first selects a group, then a sender, and then an entity within that group, returning the corresponding feature slice as the message. This converts communication from unstructured vector transmission into structured information retrieval over the sender's observation hierarchy. We instantiate this mechanism with Straight-Through Gumbel-Softmax for differentiable discrete selection and a lightweight shared projection design that attaches to standard MARL pipelines. Experiments across cooperative MARL tasks with different observation structures and coordination demands show that \textsc{HiComm} matches or outperforms representative learned communication baselines while reducing communication volume by up to

23\times

per receiver per episode.

Multi-Agent Reinforcement Learning Communication

Open paper Ask about it PDF

Abstract

Explore similar work

HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning

LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning

SCALE-COMM: Shared, Contrastively-Aligned Latent Embeddings for MARL Communication