Deciding the Value 1 Problem for sharp-acyclic Partially Observable Markov Decision Processes

Abstract : The value 1 problem is a natural decision problem in algorithmic game theory. For partially observable Markov decision processes with reachability objective, this problem is defined as follows: are there observational strategies that achieve the reachability objective with probability arbitrarily close to 1? This problem was shown undecidable recently. Our contribution is to introduce a class of partially observable Markov decision processes, namely ]-acyclic partially observable Markov decision processes, for which the value 1 problem is decidable. Our algorithm is based on the construction of a two-player perfect information game, called the knowledge game, abstracting the behaviour of a ]-acyclic partially observable Markov decision process M such that the first player has a winning strategy in the knowledge game if and only if the value of M is 1.
Type de document :
Communication dans un congrès
SOFSEM 2014, Jan 2014, Nový Smokovec, Slovakia. pp.281-292, 2014, <10.1007/978-3-319-04298-5_25>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01006394
Contributeur : Hugo Gimbert <>
Soumis le : lundi 16 juin 2014 - 08:38:09
Dernière modification le : lundi 16 juin 2014 - 11:41:10
Document(s) archivé(s) le : mardi 16 septembre 2014 - 11:01:07

Fichier

pomdp.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Hugo Gimbert, Youssouf Oualhadj. Deciding the Value 1 Problem for sharp-acyclic Partially Observable Markov Decision Processes. SOFSEM 2014, Jan 2014, Nový Smokovec, Slovakia. pp.281-292, 2014, <10.1007/978-3-319-04298-5_25>. <hal-01006394>

Partager

Métriques

Consultations de
la notice

121

Téléchargements du document

63