未折现马尔可夫决策过程的最优性方程

Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304) Pub Date : 1999-12-07 DOI:10.1109/CDC.1999.832928

M. Puterman

{"title":"未折现马尔可夫决策过程的最优性方程","authors":"M. Puterman","doi":"10.1109/CDC.1999.832928","DOIUrl":null,"url":null,"abstract":"We explore properties of the average and bias optimality equations in unichain Markov decision processes. We show that in unichain models, these equations have the same form, so that theory for gain optimality carries over to bias optimality.","PeriodicalId":137513,"journal":{"name":"Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"1999-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Optimality equations in undiscounted Markov decision processes\",\"authors\":\"M. Puterman\",\"doi\":\"10.1109/CDC.1999.832928\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We explore properties of the average and bias optimality equations in unichain Markov decision processes. We show that in unichain models, these equations have the same form, so that theory for gain optimality carries over to bias optimality.\",\"PeriodicalId\":137513,\"journal\":{\"name\":\"Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1999-12-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CDC.1999.832928\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CDC.1999.832928","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

研究了单链马尔可夫决策过程中平均最优性方程和偏优性方程的性质。我们表明，在单链模型中，这些方程具有相同的形式，因此增益最优性理论延续到偏差最优性。

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

Optimality equations in undiscounted Markov decision processes

We explore properties of the average and bias optimality equations in unichain Markov decision processes. We show that in unichain models, these equations have the same form, so that theory for gain optimality carries over to bias optimality.

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

Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304)

自引率

0.00%

发文量