Learning Approximate and Exact Numeral Systems via Reinforcement Learning
Paper i 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.

Författare

Emil Carlsson

Data Science och AI 1

Devdatt Dubhashi

Data Science och AI 1

Fredrik Johansson

Data Science och AI 1

Proceedings of the 43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021

Vol. 43

Annual Meeting of the Cognitive Science Society
Wien, Austria,

Ämneskategorier

Jämförande språkvetenskap och allmän lingvistik

Datavetenskap (datalogi)

Mer information

Senast uppdaterat

2023-04-21