Common Learning on a Continuum State Space

Erol Dogan
{"title":"Common Learning on a Continuum State Space","authors":"Erol Dogan","doi":"10.2139/ssrn.3251339","DOIUrl":null,"url":null,"abstract":"In Bayesian games the strategic outcome of a game might be sensitive to the higher order beliefs of the players. Robust strategic behavior around a perfect information type requires high enough common belief in the true state of the world. We ask whether players in a private observations framework can attain common p-belief in the true state, for p arbitrarily close to one, assuming that the state space is a continuum, the signal space is finite, and the observed process is independently and identically distributed over time. We show that, under some smoothness and convexity assumptions, if the observations are sufficiently uncorrelated, common learning fails with arbitrarily high probability. This includes the case of independent observations. The failure obtains even if any neighborhood of the true state is asymptotically assigned probability one by each agent. We also show that the failure is an almost certain if for each agent the conditional signal distributions make an open set on the set of all probability distributions on the signal set. In this case common learning fails unless there is perfect correlation. This provides justification for the presence of higher order uncertainty in Bayesian games.","PeriodicalId":260378,"journal":{"name":"Human Resource Management & Organizational Behavior eJournal","volume":"101 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Human Resource Management & Organizational Behavior eJournal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2139/ssrn.3251339","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

In Bayesian games the strategic outcome of a game might be sensitive to the higher order beliefs of the players. Robust strategic behavior around a perfect information type requires high enough common belief in the true state of the world. We ask whether players in a private observations framework can attain common p-belief in the true state, for p arbitrarily close to one, assuming that the state space is a continuum, the signal space is finite, and the observed process is independently and identically distributed over time. We show that, under some smoothness and convexity assumptions, if the observations are sufficiently uncorrelated, common learning fails with arbitrarily high probability. This includes the case of independent observations. The failure obtains even if any neighborhood of the true state is asymptotically assigned probability one by each agent. We also show that the failure is an almost certain if for each agent the conditional signal distributions make an open set on the set of all probability distributions on the signal set. In this case common learning fails unless there is perfect correlation. This provides justification for the presence of higher order uncertainty in Bayesian games.
连续状态空间上的共同学习
在贝叶斯博弈中,博弈的战略结果可能对玩家的高阶信念很敏感。围绕完美信息类型的稳健战略行为需要对世界的真实状态有足够高的共同信念。假设状态空间是连续体,信号空间是有限的,观察过程随时间独立分布,当p任意接近1时,我们问私有观察框架中的参与者是否可以在真实状态下获得共同的p信念。我们表明,在一些平滑性和凸性假设下,如果观察结果足够不相关,普通学习以任意高概率失败。这包括独立观察的情况。即使每个智能体对真实状态的任何邻域的概率渐近赋值为1,也会出现故障。我们还表明,如果每个智能体的条件信号分布在信号集中的所有概率分布的集合上形成一个开集,则故障几乎是肯定的。在这种情况下,除非有完全的相关性,否则普通的学习就失败了。这为贝叶斯博弈中存在高阶不确定性提供了理由。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
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:604180095
Book学术官方微信
小红书