Learning Approximate and Exact Numeral Systems via Reinforcement Learning
Paper in proceeding, 2021

Recent work (Xu et al., 2020) has suggested that numeral systems in different languages are shaped by a functional need for efficient communication in an information-theoretic sense. Here we take a learning-theoretic approach and show how efficient communication emerges via reinforcement learning. In our framework, two artificial agents play a Lewis signaling game where the goal is to convey a numeral concept. The agents gradually learn to communicate using reinforcement learning and the resulting numeral systems are shown to be efficient in the information-theoretic framework of Regier et al.(2015); Gibson et al. (2017). They are also shown to be similar to human numeral systems of same type. Our results thus provide a mechanistic explanation via reinforcement learning of the recent results in Xu et al. (2020) and can potentially be generalized to other semantic domains.


Emil Carlsson

Data Science and AI 1

Devdatt Dubhashi

Data Science and AI 1

Fredrik Johansson

Data Science and AI 1

Proceedings of the Annual Meeting of the Cognitive Science Society

Annual Meeting of the Cognitive Science Society
Wien, Austria,

Subject Categories

General Language Studies and Linguistics

Computer Science

More information


1/4/2022 1