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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2023.1229127/full |
| _version_ | 1797657299626491904 |
|---|---|
| author | Jun Inukai Tadahiro Taniguchi Akira Taniguchi Yoshinobu Hagiwara |
| author_facet | Jun Inukai Tadahiro Taniguchi Akira Taniguchi Yoshinobu Hagiwara |
| author_sort | Jun Inukai |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-11T17:42:28Z |
| format | Article |
| id | doaj.art-0430c57847bc437ca953c3263400f269 |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-03-11T17:42:28Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-0430c57847bc437ca953c3263400f2692023-10-18T08:56:30ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122023-10-01610.3389/frai.2023.12291271229127Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative modelsJun Inukai0Tadahiro Taniguchi1Akira Taniguchi2Yoshinobu Hagiwara3Graduate School of Information Science and Engineering, Ritsumeikan University, Kusatsu, JapanGraduate School of Information Science and Engineering, Ritsumeikan University, Kusatsu, JapanGraduate School of Information Science and Engineering, Ritsumeikan University, Kusatsu, JapanResearch Organization of Science and Technology, Ritsumeikan University, Kusatsu, JapanIn 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.https://www.frontiersin.org/articles/10.3389/frai.2023.1229127/fullsymbol emergenceemergent communicationprobabilistic generative modelslanguage gameBayesian inferencemulti-agent system |
| spellingShingle | Jun Inukai Tadahiro Taniguchi Akira Taniguchi Yoshinobu Hagiwara Recursive Metropolis-Hastings naming game: symbol emergence in a multi-agent system based on probabilistic generative models Frontiers in Artificial Intelligence symbol emergence emergent communication probabilistic generative models language game Bayesian inference multi-agent system |
| 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 | symbol emergence emergent communication probabilistic generative models language game Bayesian inference multi-agent system |
| url | https://www.frontiersin.org/articles/10.3389/frai.2023.1229127/full |
| work_keys_str_mv | AT juninukai recursivemetropolishastingsnaminggamesymbolemergenceinamultiagentsystembasedonprobabilisticgenerativemodels AT tadahirotaniguchi recursivemetropolishastingsnaminggamesymbolemergenceinamultiagentsystembasedonprobabilisticgenerativemodels AT akirataniguchi recursivemetropolishastingsnaminggamesymbolemergenceinamultiagentsystembasedonprobabilisticgenerativemodels AT yoshinobuhagiwara recursivemetropolishastingsnaminggamesymbolemergenceinamultiagentsystembasedonprobabilisticgenerativemodels |