Turnpikes in Finite Markov Decision Processes and Random Walk

IF 0.5 4区数学 Q4 STATISTICS & PROBABILITY

Theory of Probability and its Applications Pub Date : 2023-05-01 DOI:10.1137/s0040585x97t991325

A. B. Piunovskiy

引用次数: 0

Abstract

In this paper we revise the theory of turnpikes in discounted Markov decision processes, prove the turnpike theorem for the undiscounted model, and apply the results to the specific random walk.KeywordsturnpikeMarkov decision processdiscounted rewardaverage rewardrandom walkstochastic knapsack problem

查看原文本刊更多论文

有限马尔可夫决策过程和随机漫步中的收费公路

本文修正了折现马尔可夫决策过程中的收费公路理论，证明了未折现模型下的收费公路定理，并将结果应用于具体的随机漫步。马尔可夫决策过程贴现奖励平均奖励随机行走随机背包问题

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

Theory of Probability and its Applications 数学-统计学与概率论

CiteScore

1.00

自引率

16.70%

发文量

审稿时长

6 months

期刊介绍： Theory of Probability and Its Applications (TVP) accepts original articles and communications on the theory of probability, general problems of mathematical statistics, and applications of the theory of probability to natural science and technology. Articles of the latter type will be accepted only if the mathematical methods applied are essentially new.