A reinforcement-learning approach to efficient communication

Mikael Kågebäck, Emil Carlsson, Devdatt Dubhashi and Asad Sayeed

PLOS ONE, 2020, vol. 15, issue 7, 1-26

Abstract: 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.

Date: 2020
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0234894 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 34894&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0234894

DOI: 10.1371/journal.pone.0234894

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().