论网络结构在有界理性协调学习中的作用

Yifei Zhang, Marcos M. Vasconcelos
{"title":"论网络结构在有界理性协调学习中的作用","authors":"Yifei Zhang, Marcos M. Vasconcelos","doi":"arxiv-2403.15683","DOIUrl":null,"url":null,"abstract":"Many socioeconomic phenomena, such as technology adoption, collaborative\nproblem-solving, and content engagement, involve a collection of agents\ncoordinating to take a common action, aligning their decisions to maximize\ntheir individual goals. We consider a model for networked interactions where\nagents learn to coordinate their binary actions under a strict bound on their\nrationality. We first prove that our model is a potential game and that the\noptimal action profile is always to achieve perfect alignment at one of the two\npossible actions, regardless of the network structure. Using a stochastic\nlearning algorithm known as Log Linear Learning, where agents have the same\nfinite rationality parameter, we show that the probability of agents\nsuccessfully agreeing on the correct decision is monotonically increasing in\nthe number of network links. Therefore, more connectivity improves the accuracy\nof collective decision-making, as predicted by the phenomenon known as Wisdom\nof Crowds. Finally, we show that for a fixed number of links, a regular network\nmaximizes the probability of success. We conclude that when using a network of\nirrational agents, promoting more homogeneous connectivity improves the\naccuracy of collective decision-making.","PeriodicalId":501062,"journal":{"name":"arXiv - CS - Systems and Control","volume":"180 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"On the role of network structure in learning to coordinate with bounded rationality\",\"authors\":\"Yifei Zhang, Marcos M. Vasconcelos\",\"doi\":\"arxiv-2403.15683\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Many socioeconomic phenomena, such as technology adoption, collaborative\\nproblem-solving, and content engagement, involve a collection of agents\\ncoordinating to take a common action, aligning their decisions to maximize\\ntheir individual goals. We consider a model for networked interactions where\\nagents learn to coordinate their binary actions under a strict bound on their\\nrationality. We first prove that our model is a potential game and that the\\noptimal action profile is always to achieve perfect alignment at one of the two\\npossible actions, regardless of the network structure. Using a stochastic\\nlearning algorithm known as Log Linear Learning, where agents have the same\\nfinite rationality parameter, we show that the probability of agents\\nsuccessfully agreeing on the correct decision is monotonically increasing in\\nthe number of network links. Therefore, more connectivity improves the accuracy\\nof collective decision-making, as predicted by the phenomenon known as Wisdom\\nof Crowds. Finally, we show that for a fixed number of links, a regular network\\nmaximizes the probability of success. We conclude that when using a network of\\nirrational agents, promoting more homogeneous connectivity improves the\\naccuracy of collective decision-making.\",\"PeriodicalId\":501062,\"journal\":{\"name\":\"arXiv - CS - Systems and Control\",\"volume\":\"180 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-03-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Systems and Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2403.15683\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Systems and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2403.15683","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

许多社会经济现象,如技术采用、协作解决问题和内容参与,都涉及一系列代理协调采取共同行动,使其决策最大限度地实现各自的目标。我们考虑了一个网络互动模型,在这个模型中,代理学会在严格的理性约束下协调他们的二元行动。我们首先证明了我们的模型是一个潜在博弈,而且无论网络结构如何,最佳行动轮廓总是在两个可能行动中的一个实现完全一致。使用一种称为对数线性学习的随机学习算法(其中代理具有相同的无限理性参数),我们证明代理成功就正确决策达成一致的概率随着网络链接数量的增加而单调递增。因此,正如 "从众智慧 "现象所预测的那样,更多的连接会提高集体决策的准确性。最后,我们证明,在链接数量固定的情况下,规则网络能最大限度地提高成功概率。我们的结论是,在使用理性代理网络时,促进更多的同质性连接可以提高集体决策的准确性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
On the role of network structure in learning to coordinate with bounded rationality
Many socioeconomic phenomena, such as technology adoption, collaborative problem-solving, and content engagement, involve a collection of agents coordinating to take a common action, aligning their decisions to maximize their individual goals. We consider a model for networked interactions where agents learn to coordinate their binary actions under a strict bound on their rationality. We first prove that our model is a potential game and that the optimal action profile is always to achieve perfect alignment at one of the two possible actions, regardless of the network structure. Using a stochastic learning algorithm known as Log Linear Learning, where agents have the same finite rationality parameter, we show that the probability of agents successfully agreeing on the correct decision is monotonically increasing in the number of network links. Therefore, more connectivity improves the accuracy of collective decision-making, as predicted by the phenomenon known as Wisdom of Crowds. Finally, we show that for a fixed number of links, a regular network maximizes the probability of success. We conclude that when using a network of irrational agents, promoting more homogeneous connectivity improves the accuracy of collective decision-making.
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
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信