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

TL;DR

This work tackles bandwidth-limited coordination in multi-agent reinforcement learning for robotics by introducing a gated, vector-quantized communication framework grounded in information bottleneck theory. The GVQ method learns when to communicate and how to encode messages discretely, achieving substantial bandwidth reductions while preserving task performance. Key contributions include a principled IB objective with discrete messaging, a three-component gating context, dual constraint enforcement (soft penalties and primal-dual), and extensive ablations and Pareto-front analyses demonstrating dominance across the success-bandwidth spectrum. The approach enables scalable, energy-efficient coordination and provides theoretical and empirical guidance for deploying MARL systems in resource-constrained environments such as robotic swarms and autonomous fleets.

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.

Figures (4)

• Figure 1: Performance comparison showing success rates across communication methods. Our GVQ approach achieves 38.75% success rate, representing 181.8% improvement over no-communication baseline (13.75%) with statistical significance $p < 0.001$. Error bars show 95% bootstrap confidence intervals across 8 random seeds.
• Figure 2: Pareto frontier analysis showing success rate vs bandwidth trade-offs with 95% confidence bands. Our method (red curve) dominates all baselines across the entire feasible region, achieving 41.4% bandwidth reduction (800 vs 2800 bits) while maintaining superior performance. The analysis reveals three distinct operating regimes: bandwidth-limited ($< 400$ bits), balanced (400-1200 bits), and bandwidth-abundant ($> 1200$ bits). Dominance analysis shows our method achieves higher success rates at 87% of shared budget points.
• Figure 3: Detailed ablation study results showing (a) component contributions with statistical significance testing, (b) context component analysis revealing the importance of coordination estimates and message history, (c) threshold sensitivity analysis demonstrating optimal performance at $\tau = 0.5$, and (d) codebook size trade-offs between expressiveness and bandwidth efficiency.
• Figure 4: Codebook health and semantic structure analysis showing (a) token usage distribution with entropy 3.1 bits, (b) semantic clustering of tokens into four categories (target discovery, obstacle avoidance, coordination, status updates), (c) dead code fraction remaining below 5% throughout training, and (d) information preservation ratio $\rho = I(S;M)/I(S;Z) = 0.88$ for our $K=16$ configuration.