Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces

Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces

We study the policy iteration algorithm (PIA) for continuous-time jump Markov decision processes in general state and action spaces. The corresponding transition rates are allowed to be unbounded, and the reward rates may have neither upper nor lower bounds. The criterion that we are concerned with...

Full description

Bibliographic Details
Main Authors: Quanxin Zhu, Xinsong Yang, Chuangxia Huang
Format: Article
Language:English
Published: Hindawi Limited 2009-01-01
Series:Abstract and Applied Analysis
Online Access:http://dx.doi.org/10.1155/2009/103723
id doaj-e8d529083c7943c5adc1318014d46c1e
record_format Article
spelling doaj-e8d529083c7943c5adc1318014d46c1e2020-11-24T21:21:48ZengHindawi LimitedAbstract and Applied Analysis1085-33751687-04092009-01-01200910.1155/2009/103723103723Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish SpacesQuanxin Zhu0Xinsong Yang1Chuangxia Huang2Department of Mathematics, Ningbo University, Ningbo 315211, ChinaDepartment of Mathematics, Honghe University, Mengzi 661100, ChinaThe College of Mathematics and Computing Science, Changsha University of Science and Technology, Changsha 410076, ChinaWe study the policy iteration algorithm (PIA) for continuous-time jump Markov decision processes in general state and action spaces. The corresponding transition rates are allowed to be unbounded, and the reward rates may have neither upper nor lower bounds. The criterion that we are concerned with is expected average reward. We propose a set of conditions under which we first establish the average reward optimality equation and present the PIA. Then under two slightly different sets of conditions we show that the PIA yields the optimal (maximum) reward, an average optimal stationary policy, and a solution to the average reward optimality equation.http://dx.doi.org/10.1155/2009/103723
collection DOAJ
language English
format Article
sources DOAJ
author Quanxin Zhu
Xinsong Yang
Chuangxia Huang
spellingShingle Quanxin Zhu
Xinsong Yang
Chuangxia Huang
Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces
Abstract and Applied Analysis
author_facet Quanxin Zhu
Xinsong Yang
Chuangxia Huang
author_sort Quanxin Zhu
title Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces
title_short Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces
title_full Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces
title_fullStr Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces
title_full_unstemmed Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces
title_sort policy iteration for continuous-time average reward markov decision processes in polish spaces
publisher Hindawi Limited
series Abstract and Applied Analysis
issn 1085-3375
1687-0409
publishDate 2009-01-01
description We study the policy iteration algorithm (PIA) for continuous-time jump Markov decision processes in general state and action spaces. The corresponding transition rates are allowed to be unbounded, and the reward rates may have neither upper nor lower bounds. The criterion that we are concerned with is expected average reward. We propose a set of conditions under which we first establish the average reward optimality equation and present the PIA. Then under two slightly different sets of conditions we show that the PIA yields the optimal (maximum) reward, an average optimal stationary policy, and a solution to the average reward optimality equation.
url http://dx.doi.org/10.1155/2009/103723
work_keys_str_mv AT quanxinzhu policyiterationforcontinuoustimeaveragerewardmarkovdecisionprocessesinpolishspaces
AT xinsongyang policyiterationforcontinuoustimeaveragerewardmarkovdecisionprocessesinpolishspaces
AT chuangxiahuang policyiterationforcontinuoustimeaveragerewardmarkovdecisionprocessesinpolishspaces
_version_ 1725998151174717440

Similar Items