A reinforcement-learning approach to efficient communication
Journal article, 2020

We present a multi-agent computational approach to partitioning semantic spaces using reinforcement-learning (RL). Two agents communicate using a finite linguistic vocabulary in order to convey a concept. This is tested in the color domain, and a natural reinforcement learning mechanism is shown to converge to a scheme that achieves a near-optimal trade-off of simplicity versus communication efficiency. Results are presented both on the communication efficiency as well as on analyses of the resulting partitions of the color space. The effect of varying environmental factors such as noise is also studied. These results suggest that RL offers a powerful and flexible computational framework that can contribute to the development of communication schemes for color names that are near-optimal in an information-theoretic sense and may shape color-naming systems across languages. Our approach is not specific to color and can be used to explore cross-language variation in other semantic domains.


Mikael Kågebäck

Chalmers, Computer Science and Engineering (Chalmers), Data Science

Emil Carlsson

Chalmers, Computer Science and Engineering (Chalmers), Data Science

Devdatt Dubhashi

Chalmers, Computer Science and Engineering (Chalmers), Data Science

Asad Sayeed

University of Gothenburg


1932-6203 (ISSN)

Vol. 15 7 e0234894

Subject Categories

Language Technology (Computational Linguistics)

Computer Science

Computer Systems





More information

Latest update

9/9/2020 1