Learning multi-agent communication via graph contrastive learning

Wei Du

doi:10.1016/j.patcog.2025.112093

Learning multi-agent communication via graph contrastive learning

2025-07-06

0

PRE

AI

DOI：10.1016/j.patcog.2025.112093

Original

Original request for help

Save

Abstract

En 中文

Recently, communication learning has emerged as a successful tool for tackling complex tasks in multi-agent reinforcement learning (MARL). Many MARL methods use graph neural networks (GNNs) to build a communication learning framework where agents and communication channels can be represented as nodes and edges in a graph. However, most GNN-based MARL methods simply aggregate features of neighboring agents to obtain message representations, which may not extract enough useful information. To tackle this problem, this paper investigates how to extract expressive information from neighboring agents to obtain high-quality message representations. Inspired by the recent success of contrastive learning methods, in this paper, we propose a multi-agent communication protocol via graph contrastive learning (MAGE), which utilizes contrast objectives to learn optimal message representations, considering feature and topological level. At the feature level, we corrupt agent features by adding more noise to insignificant neighboring agent features, to encourage the agent to recognize significant information. At the topological level, we adaptively remove edges by assigning larger removal probabilities to insignificant edges to highlight significant communication structures. Experiments across diverse benchmarks confirm that MAGE outperforms existing GNN-based MARL methods.

Keywords:

graph neural networks

multi-agent reinforcement learning

communication learning

contrastive learning

message representation

Learning multi-agent communication via graph contrastive learning

Abstract

Journal

Organization