具有风险敏感性的子马尔可夫决策过程的最优序列

IF 2.5 3区计算机科学 Q3 AUTOMATION & CONTROL SYSTEMS

Systems & Control Letters Pub Date : 2025-09-24 DOI:10.1016/j.sysconle.2025.106245

Tanhao Huang, Jinwen Chen

{"title":"具有风险敏感性的子马尔可夫决策过程的最优序列","authors":"Tanhao Huang, Jinwen Chen","doi":"10.1016/j.sysconle.2025.106245","DOIUrl":null,"url":null,"abstract":"<div><div>This paper deals with sub-Markov decision processes with risk-sensitivity. The processes are not assumed to be communicating, thus the optimal average reward <span><math><mrow><msup><mrow><mi>J</mi></mrow><mrow><mo>∗</mo></mrow></msup><mrow><mo>(</mo><mi>x</mi><mo>)</mo></mrow></mrow></math></span> may depend on the initial state <span><math><mi>x</mi></math></span>. The aim of this paper is to characterize this dependence. It is shown that the values of <span><math><msup><mrow><mi>J</mi></mrow><mrow><mo>∗</mo></mrow></msup></math></span> are determined by a system of Poisson equations. By partitioning the state space in a proper way we derive such equations and obtain the associated optimal sequence. The partition of the state space is constructive which is closely related to the state communication, transience or absorption.</div></div>","PeriodicalId":49450,"journal":{"name":"Systems & Control Letters","volume":"205 ","pages":"Article 106245"},"PeriodicalIF":2.5000,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An optimal sequence for sub-Markov decision processes with risk sensitivity\",\"authors\":\"Tanhao Huang, Jinwen Chen\",\"doi\":\"10.1016/j.sysconle.2025.106245\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>This paper deals with sub-Markov decision processes with risk-sensitivity. The processes are not assumed to be communicating, thus the optimal average reward <span><math><mrow><msup><mrow><mi>J</mi></mrow><mrow><mo>∗</mo></mrow></msup><mrow><mo>(</mo><mi>x</mi><mo>)</mo></mrow></mrow></math></span> may depend on the initial state <span><math><mi>x</mi></math></span>. The aim of this paper is to characterize this dependence. It is shown that the values of <span><math><msup><mrow><mi>J</mi></mrow><mrow><mo>∗</mo></mrow></msup></math></span> are determined by a system of Poisson equations. By partitioning the state space in a proper way we derive such equations and obtain the associated optimal sequence. The partition of the state space is constructive which is closely related to the state communication, transience or absorption.</div></div>\",\"PeriodicalId\":49450,\"journal\":{\"name\":\"Systems & Control Letters\",\"volume\":\"205 \",\"pages\":\"Article 106245\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2025-09-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Systems & Control Letters\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0167691125002270\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Systems & Control Letters","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167691125002270","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}

引用次数: 0

摘要

本文研究具有风险敏感性的子马尔可夫决策过程。这些过程不被假设为通信，因此最优平均奖励J * (x)可能依赖于初始状态x。本文的目的是表征这种依赖性。证明了J *的值是由泊松方程组决定的。通过对状态空间进行适当的划分，导出了这些方程，并得到了相应的最优序列。状态空间的划分是建设性的，与状态的传播、暂态或吸收密切相关。

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

An optimal sequence for sub-Markov decision processes with risk sensitivity

This paper deals with sub-Markov decision processes with risk-sensitivity. The processes are not assumed to be communicating, thus the optimal average reward

J^{*} (x)

may depend on the initial state

x

. The aim of this paper is to characterize this dependence. It is shown that the values of

J^{*}

are determined by a system of Poisson equations. By partitioning the state space in a proper way we derive such equations and obtain the associated optimal sequence. The partition of the state space is constructive which is closely related to the state communication, transience or absorption.

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

Systems & Control Letters 工程技术-运筹学与管理科学

CiteScore

4.60

自引率

3.80%

发文量

144

审稿时长

6 months

期刊介绍： Founded in 1981 by two of the pre-eminent control theorists, Roger Brockett and Jan Willems, Systems & Control Letters is one of the leading journals in the field of control theory. The aim of the journal is to allow dissemination of relatively concise but highly original contributions whose high initial quality enables a relatively rapid review process. All aspects of the fields of systems and control are covered, especially mathematically-oriented and theoretical papers that have a clear relevance to engineering, physical and biological sciences, and even economics. Application-oriented papers with sophisticated and rigorous mathematical elements are also welcome.