Emergence of Writing Systems Through Multi-Agent Cooperation

TL;DR

This paper demonstrates how artificial agents can develop writing systems through cooperative referential games, analyzing how game rules influence the structure of emergent writing systems.

Contribution

It introduces a novel setup for studying the emergence of writing systems in artificial agents and proposes a metric to analyze their taxonomy.

Findings

Agents successfully learn to coordinate using emergent writing systems.

Game rules significantly influence the structure of the developed writing systems.

The proposed consistency metric helps classify different types of emergent writing.

Abstract

Learning to communicate is considered an essential task to develop a general AI. While recent literature in language evolution has studied emergent language through discrete or continuous message symbols, there has been little work in the emergence of writing systems in artificial agents. In this paper, we present a referential game setup with two agents, where the mode of communication is a written language system that emerges during the play. We show that the agents can learn to coordinate successfully using this mode of communication. Further, we study how the game rules affect the writing system taxonomy by proposing a consistency metric.