Learning Multi-Agent Communication Protocol: Study on Information Entropy Efficiency in MARL

2026-06-05

AI Summary

This work addresses the lack of quantitative evaluation of communication efficiency in existing multi-agent reinforcement learning (MARL) methods, which often achieve performance gains at the cost of high communication overhead. The authors propose the Information Entropy Efficiency Index (IEI)—a novel metric defined as the ratio of task performance to message entropy—and integrate it directly into the MARL training objective. By jointly optimizing task performance and IEI within the loss function, agents learn to autonomously develop low-entropy, communication-efficient protocols. Experimental results demonstrate that the proposed approach achieves task performance comparable to or better than baseline methods across multiple MARL algorithms while substantially improving communication efficiency, thereby confirming the feasibility of simultaneously attaining high performance and efficient communication.

Abstract

Multi-Agent Systems (MAS) have emerged as a fundamental paradigm for distributed problem-solving, where autonomous agents collaborate to achieve complex objectives. Within this framework, Multi-Agent Reinforcement Learning (MARL) with communication has demonstrated remarkable success in cooperative tasks. However, existing approaches predominantly pursue performance gains through increasingly complex architectures and expanding communication overhead, lacking principled metrics to evaluate the efficiency of information exchange. In this paper, we focus on enabling agents to learn efficient multi-agent communication protocols that balance performance and information compactness. We propose the Information Entropy Efficiency Index (IEI), a novel metric that quantifies the ratio between message entropy and task performance in learned communication protocols. A lower IEI indicates more compact and efficient message representations. By incorporating IEI into training loss functions, we encourage agents to develop communication protocols that achieve high performance with improved communication efficiency. Extensive experiments across diverse MARL algorithms demonstrate that our approach achieves equivalent or superior task performance compared to baseline methods while improving communication efficiency. These findings challenge the prevailing assumption that performance improvements require complex architectures or increased communication overhead and highlight the potential of improving both task success and communication efficiency to enable scalable MAS.

Problem

• Multi-Agent Reinforcement Learning
• Communication Efficiency
• Information Entropy
• Message Compactness
• Scalable Multi-Agent Systems

Innovation

• Information Entropy Efficiency
• Multi-Agent Reinforcement Learning
• Communication Efficiency
• Message Compactness
• IEI