Back to Search Start Over

Blackwell optimality in Markov decision processes with partial observation

Authors :
Nicolas Vieille
Dinah Rosenberg
Eilon Solan
Laboratoire Analyse, Géométrie et Applications (LAGA)
Université Paris 8 Vincennes-Saint-Denis (UP8)-Centre National de la Recherche Scientifique (CNRS)-Institut Galilée-Université Paris 13 (UP13)
Groupement de Recherche et d'Etudes en Gestion à HEC (GREGH)
Ecole des Hautes Etudes Commerciales (HEC Paris)-Centre National de la Recherche Scientifique (CNRS)
Department of Statitics and Operation Research, Tel Aviv University
Tel-Abib University
Source :
Ann. Statist. 30, no. 4 (2002), 1178-1193, Annals of Statistics, Annals of Statistics, Institute of Mathematical Statistics, 2002, Vol.30,n°4, pp.1178-1193. ⟨10.1214/aos/1031689022⟩
Publication Year :
2002
Publisher :
The Institute of Mathematical Statistics, 2002.

Abstract

A Blackwell $\epsilon$-optimal strategy in a Markov Decision Process is a strategy that is $\epsilon$-optimal for every discount factor sufficiently close to 1. ¶ We prove the existence of Blackwell $\epsilon$-optimal strategies in finite Markov Decision Processes with partial observation.

Details

Language :
English
ISSN :
00905364 and 21688966
Database :
OpenAIRE
Journal :
Ann. Statist. 30, no. 4 (2002), 1178-1193, Annals of Statistics, Annals of Statistics, Institute of Mathematical Statistics, 2002, Vol.30,n°4, pp.1178-1193. ⟨10.1214/aos/1031689022⟩
Accession number :
edsair.doi.dedup.....9c8b5fd29c6d3037fdd6318ada8a71cf
Full Text :
https://doi.org/10.1214/aos/1031689022⟩