Efficient Communication via Reinforcement Learning
Licentiatavhandling, 2022

Why do languages partition mental concepts into words the way the do? Recent works have taken a information-theoretic view on human language and suggested that it is shaped by the need for efficient communication. This means that human language is shaped by a simultaneous pressure for being informative, while also being simple in order to minimize the cognitive load.


In this thesis we combine the information-theoretic perspective on language with recent advances in deep multi-agent reinforcement learning. We explore how efficient communication emerges between two artificial agents in a signaling game as a by-product of them maximizing a shared reward signal. This is tested in the domain of colors and numeral systems, two domains in which human languages tends to support efficient communication. We find that the communication developed by the artificial agents in these domains shares characteristics with human languages when it comes to efficiency and structure of semantic partitions. even though the agents lack the full perceptual and linguistic architecture of humans.


Our results offer a computational learning perspective that may complement the information-theoretic view on the structure of human languages. The results also suggests that reinforcement learning is a powerful and flexible framework that can be used to test and generate hypotheses in silico.

EDIT 8103/Online
Opponent: Noah Goodman, Associate Professor, Department of Psychology, Stanford University, USA

Författare

Emil Carlsson

Chalmers, Data- och informationsteknik, Data Science och AI

Learning Approximate and Exact Numeral Systems via Reinforcement Learning

Proceedings of the 43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021,; Vol. 43(2021)

Paper i proceeding

A reinforcement-learning approach to efficient communication

PLoS ONE,; Vol. 15(2020)

Artikel i vetenskaplig tidskrift

Ämneskategorier

Datavetenskap (datalogi)

Utgivare

Chalmers

EDIT 8103/Online

Online

Opponent: Noah Goodman, Associate Professor, Department of Psychology, Stanford University, USA

Mer information

Senast uppdaterat

2022-06-29