Translator Disclaimer
November, 1974 Incomplete Information in Markovian Decision Models
Detlef Rhenius
Ann. Statist. 2(6): 1327-1334 (November, 1974). DOI: 10.1214/aos/1176342886

Abstract

If a set of states is given in a problem of dynamic programming in which each state can be observed only partially, the given model is generally transformed into a new model with completely observed states. In this article a method is introduced with which Markov models of dynamic programming can be transformed and which preserves the Markov property. The method applies to relatively general sets of states.

Citation

Download Citation

Detlef Rhenius. "Incomplete Information in Markovian Decision Models." Ann. Statist. 2 (6) 1327 - 1334, November, 1974. https://doi.org/10.1214/aos/1176342886

Information

Published: November, 1974
First available in Project Euclid: 12 April 2007

zbMATH: 0294.49007
MathSciNet: MR378840
Digital Object Identifier: 10.1214/aos/1176342886

Subjects:
Primary: 49C15
Secondary: 49A05

Rights: Copyright © 1974 Institute of Mathematical Statistics

JOURNAL ARTICLE
8 PAGES


SHARE
Vol.2 • No. 6 • November, 1974
Back to Top