有限地平线零和随机博弈中的恒定回报特性

arXiv - MATH - Optimization and Control Pub Date : 2024-09-09 DOI:arxiv-2409.05683

Thomas Ragel, Bruno Ziliotto

{"title":"有限地平线零和随机博弈中的恒定回报特性","authors":"Thomas Ragel, Bruno Ziliotto","doi":"arxiv-2409.05683","DOIUrl":null,"url":null,"abstract":"This paper examines finite zero-sum stochastic games and demonstrates that\nwhen the game's duration is sufficiently long, there exists a pair of\napproximately optimal strategies such that the expected average payoff at any\npoint in the game remains close to the value. This property, known as the\n\\textit{constant payoff property}, was previously established only for\nabsorbing games and discounted stochastic games.","PeriodicalId":501286,"journal":{"name":"arXiv - MATH - Optimization and Control","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Constant Payoff Property in Zero-Sum Stochastic Games with a Finite Horizon\",\"authors\":\"Thomas Ragel, Bruno Ziliotto\",\"doi\":\"arxiv-2409.05683\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper examines finite zero-sum stochastic games and demonstrates that\\nwhen the game's duration is sufficiently long, there exists a pair of\\napproximately optimal strategies such that the expected average payoff at any\\npoint in the game remains close to the value. This property, known as the\\n\\\\textit{constant payoff property}, was previously established only for\\nabsorbing games and discounted stochastic games.\",\"PeriodicalId\":501286,\"journal\":{\"name\":\"arXiv - MATH - Optimization and Control\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - MATH - Optimization and Control\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.05683\",\"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 - MATH - Optimization and Control","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.05683","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

本文研究了有限零和随机博弈，并证明当博弈持续时间足够长时，存在一对近似最优的策略，使得博弈中任何一点的期望平均报酬都保持在接近值的水平。这一性质被称为 "不变报酬性质"（the/textit{constant payoff property}），以前只在吸收博弈和贴现随机博弈中被证实。

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

Constant Payoff Property in Zero-Sum Stochastic Games with a Finite Horizon

This paper examines finite zero-sum stochastic games and demonstrates that when the game's duration is sufficiently long, there exists a pair of approximately optimal strategies such that the expected average payoff at any point in the game remains close to the value. This property, known as the \textit{constant payoff property}, was previously established only for absorbing games and discounted stochastic games.

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

arXiv - MATH - Optimization and Control

自引率

0.00%

发文量