Multi-Agent Reinforcement Learning as a Computational Tool for Language Evolution Research: Historical Context and Future Challenges

TL;DR

This paper reviews how recent multi-agent reinforcement learning models can serve as tools for understanding language evolution, connecting current advances with historical research and outlining future challenges.

Contribution

It contextualizes recent MARL models within the history of language evolution research and identifies key challenges for future studies.

Findings

MARL models are increasingly relevant for language evolution studies

Historical context reveals gaps between computational models and linguistic theories

Future challenges include integrating more realistic cognitive and social factors

Abstract

Computational models of emergent communication in agent populations are currently gaining interest in the machine learning community due to recent advances in Multi-Agent Reinforcement Learning (MARL). Current contributions are however still relatively disconnected from the earlier theoretical and computational literature aiming at understanding how language might have emerged from a prelinguistic substance. The goal of this paper is to position recent MARL contributions within the historical context of language evolution research, as well as to extract from this theoretical and computational background a few challenges for future research.