English

Low-Bandwidth Communication Emerges Naturally in Multi-Agent Learning Systems

Multiagent Systems 2020-12-10 v2 Artificial Intelligence Machine Learning

Abstract

In this work, we study emergent communication through the lens of cooperative multi-agent behavior in nature. Using insights from animal communication, we propose a spectrum from low-bandwidth (e.g. pheromone trails) to high-bandwidth (e.g. compositional language) communication that is based on the cognitive, perceptual, and behavioral capabilities of social agents. Through a series of experiments with pursuit-evasion games, we identify multi-agent reinforcement learning algorithms as a computational model for the low-bandwidth end of the communication spectrum.

Keywords

Cite

@article{arxiv.2011.14890,
  title  = {Low-Bandwidth Communication Emerges Naturally in Multi-Agent Learning Systems},
  author = {Niko A. Grupen and Daniel D. Lee and Bart Selman},
  journal= {arXiv preprint arXiv:2011.14890},
  year   = {2020}
}

Comments

10 pages, 6 figures, Appearing in Talking to Strangers: Zero-Shot Emergent Communication Workshop NeurIPS 2020. Fixed part (a) of Figure 2 to include correct baseline reported in quantitative results section

R2 v1 2026-06-23T20:36:14.214Z