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.
Publié le : 1974-11-14
Classification:
Decision model,
concealed state space,
standard Borel space,
49C15,
49A05
@article{1176342886,
author = {Rhenius, Detlef},
title = {Incomplete Information in Markovian Decision Models},
journal = {Ann. Statist.},
volume = {2},
number = {1},
year = {1974},
pages = { 1327-1334},
language = {en},
url = {http://dml.mathdoc.fr/item/1176342886}
}
Rhenius, Detlef. Incomplete Information in Markovian Decision Models. Ann. Statist., Tome 2 (1974) no. 1, pp. 1327-1334. http://gdmltest.u-ga.fr/item/1176342886/