Towards Human-Agent Communication via the Information Bottleneck Principle
This work addresses the challenge of developing more human-like communication in AI agents, offering incremental improvements by integrating information bottleneck principles into existing neural architectures.
The paper tackled the problem of emergent communication in AI agents by incorporating principles from human language evolution, specifically balancing utility, informativeness, and complexity, and found that this approach improved convergence rates and led to human-like lexicon sizes while maintaining high utility, with VQ-VIB outperforming other discrete communication methods.
Emergent communication research often focuses on optimizing task-specific utility as a driver for communication. However, human languages appear to evolve under pressure to efficiently compress meanings into communication signals by optimizing the Information Bottleneck tradeoff between informativeness and complexity. In this work, we study how trading off these three factors -- utility, informativeness, and complexity -- shapes emergent communication, including compared to human communication. To this end, we propose Vector-Quantized Variational Information Bottleneck (VQ-VIB), a method for training neural agents to compress inputs into discrete signals embedded in a continuous space. We train agents via VQ-VIB and compare their performance to previously proposed neural architectures in grounded environments and in a Lewis reference game. Across all neural architectures and settings, taking into account communicative informativeness benefits communication convergence rates, and penalizing communicative complexity leads to human-like lexicon sizes while maintaining high utility. Additionally, we find that VQ-VIB outperforms other discrete communication methods. This work demonstrates how fundamental principles that are believed to characterize human language evolution may inform emergent communication in artificial agents.