马尔可夫决策过程中一类新的递归实用程序

Q4 Mathematics

Applicationes Mathematicae Pub Date : 2017-01-01 DOI:10.4064/AM2317-1-2017

Hubert Asienkiewicz, A. Jaśkiewicz

{"title":"马尔可夫决策过程中一类新的递归实用程序","authors":"Hubert Asienkiewicz, A. Jaśkiewicz","doi":"10.4064/AM2317-1-2017","DOIUrl":null,"url":null,"abstract":". This paper deals with Markov decision processes on a general state space under standard compactness-continuity assumptions. The pur-pose is to obtain a new class of so-called recursive utilities with the aid of the entropic risk measure. Within this framework we show that there exists a stationary policy for a discounted payoﬀ problem in the inﬁnite time horizon. Our result is illustrated by examples.","PeriodicalId":52313,"journal":{"name":"Applicationes Mathematicae","volume":"9 4 1","pages":"149-161"},"PeriodicalIF":0.0000,"publicationDate":"2017-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"A note on a new class of recursive utilities in Markov decision processes\",\"authors\":\"Hubert Asienkiewicz, A. Jaśkiewicz\",\"doi\":\"10.4064/AM2317-1-2017\",\"DOIUrl\":null,\"url\":null,\"abstract\":\". This paper deals with Markov decision processes on a general state space under standard compactness-continuity assumptions. The pur-pose is to obtain a new class of so-called recursive utilities with the aid of the entropic risk measure. Within this framework we show that there exists a stationary policy for a discounted payoﬀ problem in the inﬁnite time horizon. Our result is illustrated by examples.\",\"PeriodicalId\":52313,\"journal\":{\"name\":\"Applicationes Mathematicae\",\"volume\":\"9 4 1\",\"pages\":\"149-161\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Applicationes Mathematicae\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.4064/AM2317-1-2017\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Mathematics\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applicationes Mathematicae","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4064/AM2317-1-2017","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Mathematics","Score":null,"Total":0}

引用次数: 10

摘要

．本文研究了在标准紧连续性假设下广义状态空间上的马尔可夫决策过程。目的是借助熵风险测度获得一类新的递归效用。在这个框架内，我们证明了在无限时间范围内存在一个固定策略来解决贴现支付问题。用实例说明了我们的结果。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A note on a new class of recursive utilities in Markov decision processes

. This paper deals with Markov decision processes on a general state space under standard compactness-continuity assumptions. The pur-pose is to obtain a new class of so-called recursive utilities with the aid of the entropic risk measure. Within this framework we show that there exists a stationary policy for a discounted payoﬀ problem in the inﬁnite time horizon. Our result is illustrated by examples.

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

Applicationes Mathematicae Mathematics-Applied Mathematics

CiteScore

0.30

自引率

0.00%

发文量