Language games meet multi-agent reinforcement learning: A case study for the naming game

Abstract

Today, computational models of emergent communication in populations of autonomous agents are studied through two main methodological paradigms: multi-agent reinforcement learning (MARL) and the language game paradigm. While both paradigms share their main objectives and employ strikingly similar methods, the interaction between both communities has so far been surprisingly limited. This can to a large extent be ascribed to the use of different terminologies and experimental designs, which sometimes hinder the detection and interpretation of one another's results and progress. Through this paper, we aim to remedy this situation by (1) formulating the challenge of re-conceptualising the language game experimental paradigm in the framework of MARL, and by (2) providing both an alignment between their terminologies and an MARL-based reformulation of the canonical naming game experiment. Tackling this challenge will enable future language game experiments to benefit from the rapid and promising methodological advances in the MARL community, while it will enable future MARL experiments on learning emergent communication to benefit from the insights and results gained through language game experiments. We strongly believe that this cross-pollination has the potential to lead to major breakthroughs in the modelling of how human-like languages can emerge and evolve in multi-agent systems.