Bandwidth-Efficient Multi-Agent Communication through Information Bottleneck and Vector Quantization

TL;DR

This paper introduces a novel framework combining information bottleneck theory and vector quantization to enable bandwidth-efficient, selective communication in multi-agent reinforcement learning, significantly improving coordination performance under communication constraints.

Contribution

It presents a new method that learns to compress and discretize messages while preserving critical information, with a dynamic gating mechanism for context-aware communication.

Findings

Achieves 181.8% performance improvement over no-communication baselines.

Reduces bandwidth usage by 41.4%.

Outperforms existing strategies across success-bandwidth spectrum.

Abstract

Multi-agent reinforcement learning systems deployed in real-world robotics applications face severe communication constraints that significantly impact coordination effectiveness. We present a framework that combines information bottleneck theory with vector quantization to enable selective, bandwidth-efficient communication in multi-agent environments. Our approach learns to compress and discretize communication messages while preserving task-critical information through principled information-theoretic optimization. We introduce a gated communication mechanism that dynamically determines when communication is necessary based on environmental context and agent states. Experimental evaluation on challenging coordination tasks demonstrates that our method achieves 181.8% performance improvement over no-communication baselines while reducing bandwidth usage by 41.4%. Comprehensive Pareto frontier analysis shows dominance across the entire success-bandwidth spectrum with area-under-curve of 0.198 vs 0.142 for next-best methods. Our approach significantly outperforms existing communication strategies and establishes a theoretically grounded framework for deploying multi-agent systems in bandwidth-constrained environments such as robotic swarms, autonomous vehicle fleets, and distributed sensor networks.