Emergent Communication under Competition

TL;DR

This paper demonstrates that communication can emerge between competitive agents under certain conditions, challenging previous beliefs that standard RL algorithms cannot facilitate such communication in competitive settings.

Contribution

It introduces a modified sender-receiver game to explore partially-competitive scenarios, showing communication can occur and highlighting the importance of cooperation and mutual benefit.

Findings

Communication correlates with cooperation levels.

Communication can emerge in partially-competitive scenarios.

Successful negotiation requires mutual benefit for communication to develop.

Abstract

The literature in modern machine learning has only negative results for learning to communicate between competitive agents using standard RL. We introduce a modified sender-receiver game to study the spectrum of partially-competitive scenarios and show communication can indeed emerge in a competitive setting. We empirically demonstrate three key takeaways for future research. First, we show that communication is proportional to cooperation, and it can occur for partially competitive scenarios using standard learning algorithms. Second, we highlight the difference between communication and manipulation and extend previous metrics of communication to the competitive case. Third, we investigate the negotiation game where previous work failed to learn communication between independent agents (Cao et al., 2018). We show that, in this setting, both agents must benefit from communication for it to emerge; and, with a slight modification to the game, we demonstrate successful communication between competitive agents. We hope this work overturns misconceptions and inspires more research in competitive emergent communication.