Revisiting Populations in Multi-Agent Communication

Paul Michel, Mathieu Rita, Kory Wallace Mathewson, Olivier Tieleman, Angeliki Lazaridou

Keywords: Emergent Communication, Multi-agent Communication, Populations

Abstract: Despite evidence from sociolinguistics that larger groups of speakers tend to develop more structured languages, the use of populations has failed to yield significant benefits in emergent multi-agent communication. In this paper we reassess the validity of the standard training protocol and illustrate its limitations. Specifically, we analyze population-level communication at the equilibrium in sender-receiver Lewis games. We find that receivers co-adapt to senders they are interacting with, which limits the effect of the population. Informed by this analysis, we propose an alternative training protocol based on ``partitioning'' agents. Partitioning isolates sender-receiver pairs, limits co-adaptation, and results in a new global optimization objective where agents maximize (1) their respective "internal" communication accuracy and (2) their alignment with other agents. In experiments, we find that agents trained in partitioned populations are able to communicate successfully with new agents which they have never interacted with and tend to develop a shared language. Moreover, we observe that larger populations develop languages that are more compositional. Our findings suggest that scaling up to populations in multi-agent can be beneficial, but that it matters how we scale up.

TL;DR: Artificial agents trained to communicate in a population develop a more structured language when we regulate co-adaptation