Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision Processes

It is proved that the optimal policy of a Markov decision process where the state space is truncated, will approximate the policy in case of no truncation.

Bibliographic Details
Main Author:	Sjur D. Flåm
Format:	Article
Language:	English
Published:	Norwegian Society of Automatic Control 1987-04-01
Series:	Modeling, Identification and Control
Subjects:	Markov decision processes approximation
Online Access:	http://www.mic-journal.no/PDF/1987/MIC-1987-2-4.pdf

id	doaj-5d74dcd2fbc44bfa96902cbed2e85045
record_format	Article
spelling	doaj-5d74dcd2fbc44bfa96902cbed2e850452020-11-24T22:40:08ZengNorwegian Society of Automatic ControlModeling, Identification and Control0332-73531890-13281987-04-018211712310.4173/mic.1987.2.4Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision ProcessesSjur D. FlåmIt is proved that the optimal policy of a Markov decision process where the state space is truncated, will approximate the policy in case of no truncation. http://www.mic-journal.no/PDF/1987/MIC-1987-2-4.pdfMarkov decision processesapproximation
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Sjur D. Flåm
spellingShingle	Sjur D. Flåm Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision Processes Modeling, Identification and Control Markov decision processes approximation
author_facet	Sjur D. Flåm
author_sort	Sjur D. Flåm
title	Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision Processes
title_short	Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision Processes
title_full	Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision Processes
title_fullStr	Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision Processes
title_full_unstemmed	Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision Processes
title_sort	finite state approximations for countable state infinite horizon discounted markov decision processes
publisher	Norwegian Society of Automatic Control
series	Modeling, Identification and Control
issn	0332-7353 1890-1328
publishDate	1987-04-01
description	It is proved that the optimal policy of a Markov decision process where the state space is truncated, will approximate the policy in case of no truncation.
topic	Markov decision processes approximation
url	http://www.mic-journal.no/PDF/1987/MIC-1987-2-4.pdf
work_keys_str_mv	AT sjurdflam finitestateapproximationsforcountablestateinfinitehorizondiscountedmarkovdecisionprocesses
_version_	1725705778081300480

Finite State Approximations for Countable State Infinite Horizon Discounted Markov Decision Processes

Similar Items