语言游戏与多智能体强化学习——以命名游戏为例

IF 2.1 0 LANGUAGE & LINGUISTICS Journal of Language Evolution Pub Date : 2023-04-18 DOI:10.1093/jole/lzad001
Paul Van Eecke, Katrien Beuls, Jérôme Botoko Ekila, Roxana Rădulescu
{"title":"语言游戏与多智能体强化学习——以命名游戏为例","authors":"Paul Van Eecke, Katrien Beuls, Jérôme Botoko Ekila, Roxana Rădulescu","doi":"10.1093/jole/lzad001","DOIUrl":null,"url":null,"abstract":"\n Today, computational models of emergent communication in populations of autonomous agents are studied through two main methodological paradigms: multi-agent reinforcement learning (MARL) and the language game paradigm. While both paradigms share their main objectives and employ strikingly similar methods, the interaction between both communities has so far been surprisingly limited. This can to a large extent be ascribed to the use of different terminologies and experimental designs, which sometimes hinder the detection and interpretation of one another’s results and progress. Through this paper, we aim to remedy this situation by (1) formulating the challenge of re-conceptualising the language game experimental paradigm in the framework of MARL, and by (2) providing both an alignment between their terminologies and an MARL−based reformulation of the canonical naming game experiment. Tackling this challenge will enable future language game experiments to benefit from the rapid and promising methodological advances in the MARL community, while it will enable future MARL experiments on learning emergent communication to benefit from the insights and results gained through language game experiments. We strongly believe that this cross-pollination has the potential to lead to major breakthroughs in the modelling of how human-like languages can emerge and evolve in multi-agent systems.","PeriodicalId":37118,"journal":{"name":"Journal of Language Evolution","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2023-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Language games meet multi-agent reinforcement learning: A case study for the naming game\",\"authors\":\"Paul Van Eecke, Katrien Beuls, Jérôme Botoko Ekila, Roxana Rădulescu\",\"doi\":\"10.1093/jole/lzad001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n Today, computational models of emergent communication in populations of autonomous agents are studied through two main methodological paradigms: multi-agent reinforcement learning (MARL) and the language game paradigm. While both paradigms share their main objectives and employ strikingly similar methods, the interaction between both communities has so far been surprisingly limited. This can to a large extent be ascribed to the use of different terminologies and experimental designs, which sometimes hinder the detection and interpretation of one another’s results and progress. Through this paper, we aim to remedy this situation by (1) formulating the challenge of re-conceptualising the language game experimental paradigm in the framework of MARL, and by (2) providing both an alignment between their terminologies and an MARL−based reformulation of the canonical naming game experiment. Tackling this challenge will enable future language game experiments to benefit from the rapid and promising methodological advances in the MARL community, while it will enable future MARL experiments on learning emergent communication to benefit from the insights and results gained through language game experiments. We strongly believe that this cross-pollination has the potential to lead to major breakthroughs in the modelling of how human-like languages can emerge and evolve in multi-agent systems.\",\"PeriodicalId\":37118,\"journal\":{\"name\":\"Journal of Language Evolution\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2023-04-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Language Evolution\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/jole/lzad001\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"0\",\"JCRName\":\"LANGUAGE & LINGUISTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Language Evolution","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/jole/lzad001","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"LANGUAGE & LINGUISTICS","Score":null,"Total":0}
引用次数: 0

摘要

目前,自主智能体群体中紧急通信的计算模型主要通过两种方法范式进行研究:多智能体强化学习(MARL)和语言游戏范式。虽然这两种模式都有共同的主要目标,并采用惊人相似的方法,但到目前为止,这两个社区之间的互动却令人惊讶地有限。这在很大程度上可以归因于使用不同的术语和实验设计,这有时会阻碍发现和解释彼此的结果和进展。通过本文,我们的目标是通过(1)提出在MARL框架内重新概念化语言游戏实验范式的挑战,以及(2)提供他们的术语之间的一致性和基于MARL的规范命名游戏实验的重新表述来纠正这种情况。解决这一挑战将使未来的语言游戏实验受益于MARL社区快速而有前途的方法进步,同时它将使未来的MARL学习紧急交流的实验受益于通过语言游戏实验获得的见解和结果。我们坚信,这种交叉授粉有可能在模拟类人语言如何在多智能体系统中出现和进化方面取得重大突破。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Language games meet multi-agent reinforcement learning: A case study for the naming game
Today, computational models of emergent communication in populations of autonomous agents are studied through two main methodological paradigms: multi-agent reinforcement learning (MARL) and the language game paradigm. While both paradigms share their main objectives and employ strikingly similar methods, the interaction between both communities has so far been surprisingly limited. This can to a large extent be ascribed to the use of different terminologies and experimental designs, which sometimes hinder the detection and interpretation of one another’s results and progress. Through this paper, we aim to remedy this situation by (1) formulating the challenge of re-conceptualising the language game experimental paradigm in the framework of MARL, and by (2) providing both an alignment between their terminologies and an MARL−based reformulation of the canonical naming game experiment. Tackling this challenge will enable future language game experiments to benefit from the rapid and promising methodological advances in the MARL community, while it will enable future MARL experiments on learning emergent communication to benefit from the insights and results gained through language game experiments. We strongly believe that this cross-pollination has the potential to lead to major breakthroughs in the modelling of how human-like languages can emerge and evolve in multi-agent systems.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Language Evolution
Journal of Language Evolution Social Sciences-Linguistics and Language
CiteScore
4.50
自引率
7.70%
发文量
8
期刊最新文献
Derivational morphology and suffixing bias on linguistic and nonlinguistic material Bayesian phylogenetic analysis of pitch-accent systems based on accentual class merger: a new method applied to Japanese dialects The evolution of evolutionary linguistics Evolutionary pathways of complexity in gender systems Correction to: The scientometric landscape of Evolang: A comprehensive database of the Evolang conference
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1