Cargando…

Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models

In the studies on symbol emergence and emergent communication in a population of agents, a computational model was employed in which agents participate in various language games. Among these, the Metropolis-Hastings naming game (MHNG) possesses a notable mathematical property: symbol emergence throu...

Descripción completa

Detalles Bibliográficos
Autores principales: Inukai, Jun, Taniguchi, Tadahiro, Taniguchi, Akira, Hagiwara, Yoshinobu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10619661/
https://www.ncbi.nlm.nih.gov/pubmed/37920571
http://dx.doi.org/10.3389/frai.2023.1229127
_version_ 1785130034355240960
author Inukai, Jun
Taniguchi, Tadahiro
Taniguchi, Akira
Hagiwara, Yoshinobu
author_facet Inukai, Jun
Taniguchi, Tadahiro
Taniguchi, Akira
Hagiwara, Yoshinobu
author_sort Inukai, Jun
collection PubMed
description In the studies on symbol emergence and emergent communication in a population of agents, a computational model was employed in which agents participate in various language games. Among these, the Metropolis-Hastings naming game (MHNG) possesses a notable mathematical property: symbol emergence through MHNG is proven to be a decentralized Bayesian inference of representations shared by the agents. However, the previously proposed MHNG is limited to a two-agent scenario. This paper extends MHNG to an N-agent scenario. The main contributions of this paper are twofold: (1) we propose the recursive Metropolis-Hastings naming game (RMHNG) as an N-agent version of MHNG and demonstrate that RMHNG is an approximate Bayesian inference method for the posterior distribution over a latent variable shared by agents, similar to MHNG; and (2) we empirically evaluate the performance of RMHNG on synthetic and real image data, i.e., YCB object dataset, enabling multiple agents to develop and share a symbol system. Furthermore, we introduce two types of approximations—one-sample and limited-length—to reduce computational complexity while maintaining the ability to explain communication in a population of agents. The experimental findings showcased the efficacy of RMHNG as a decentralized Bayesian inference for approximating the posterior distribution concerning latent variables, which are jointly shared among agents, akin to MHNG, although the improvement in ARI and κ coefficient is smaller in the real image dataset condition. Moreover, the utilization of RMHNG elucidated the agents' capacity to exchange symbols. Furthermore, the study discovered that even the computationally simplified version of RMHNG could enable symbols to emerge among the agents.
format Online
Article
Text
id pubmed-10619661
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-106196612023-11-02 Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models Inukai, Jun Taniguchi, Tadahiro Taniguchi, Akira Hagiwara, Yoshinobu Front Artif Intell Artificial Intelligence In the studies on symbol emergence and emergent communication in a population of agents, a computational model was employed in which agents participate in various language games. Among these, the Metropolis-Hastings naming game (MHNG) possesses a notable mathematical property: symbol emergence through MHNG is proven to be a decentralized Bayesian inference of representations shared by the agents. However, the previously proposed MHNG is limited to a two-agent scenario. This paper extends MHNG to an N-agent scenario. The main contributions of this paper are twofold: (1) we propose the recursive Metropolis-Hastings naming game (RMHNG) as an N-agent version of MHNG and demonstrate that RMHNG is an approximate Bayesian inference method for the posterior distribution over a latent variable shared by agents, similar to MHNG; and (2) we empirically evaluate the performance of RMHNG on synthetic and real image data, i.e., YCB object dataset, enabling multiple agents to develop and share a symbol system. Furthermore, we introduce two types of approximations—one-sample and limited-length—to reduce computational complexity while maintaining the ability to explain communication in a population of agents. The experimental findings showcased the efficacy of RMHNG as a decentralized Bayesian inference for approximating the posterior distribution concerning latent variables, which are jointly shared among agents, akin to MHNG, although the improvement in ARI and κ coefficient is smaller in the real image dataset condition. Moreover, the utilization of RMHNG elucidated the agents' capacity to exchange symbols. Furthermore, the study discovered that even the computationally simplified version of RMHNG could enable symbols to emerge among the agents. Frontiers Media S.A. 2023-10-18 /pmc/articles/PMC10619661/ /pubmed/37920571 http://dx.doi.org/10.3389/frai.2023.1229127 Text en Copyright © 2023 Inukai, Taniguchi, Taniguchi and Hagiwara. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Artificial Intelligence
Inukai, Jun
Taniguchi, Tadahiro
Taniguchi, Akira
Hagiwara, Yoshinobu
Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models
title Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models
title_full Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models
title_fullStr Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models
title_full_unstemmed Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models
title_short Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models
title_sort recursive metropolis-hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10619661/
https://www.ncbi.nlm.nih.gov/pubmed/37920571
http://dx.doi.org/10.3389/frai.2023.1229127
work_keys_str_mv AT inukaijun recursivemetropolishastingsnaminggamesymbolemergenceinamultiagentsystembasedonprobabilisticgenerativemodels
AT taniguchitadahiro recursivemetropolishastingsnaminggamesymbolemergenceinamultiagentsystembasedonprobabilisticgenerativemodels
AT taniguchiakira recursivemetropolishastingsnaminggamesymbolemergenceinamultiagentsystembasedonprobabilisticgenerativemodels
AT hagiwarayoshinobu recursivemetropolishastingsnaminggamesymbolemergenceinamultiagentsystembasedonprobabilisticgenerativemodels