Strong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processes - HAL-SHS - Sciences de l'Homme et de la Société Accéder directement au contenu
Article Dans Une Revue SIAM Journal on Control and Optimization Année : 2016

Strong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processes

Résumé

In several standard models of dynamic programming (gambling houses, MDPs, POMDPs), we prove the existence of a robust notion of value for the infinitely repeated problem, namely the strong uniform value. This solves two open problems. First, this shows that for any > 0, the decision-maker has a pure strategy σ which is-optimal in any n-stage problem, provided that n is big enough (this result was only known for behavior strategies, that is, strategies which use randomization). Second, for any > 0, the decision-maker can guarantee the limit of the n-stage value minus in the infinite problem where the payoff is the expectation of the inferior limit of the time average payoff.
Fichier principal
Vignette du fichier
Revision_venel_ziliotto5.pdf (447.69 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01395429 , version 1 (10-11-2016)

Identifiants

Citer

Xavier Venel, Bruno Ziliotto. Strong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processes. SIAM Journal on Control and Optimization, 2016, 54 (4), pp.1983-2008. ⟨10.1137/15M1043340⟩. ⟨hal-01395429⟩

Relations

179 Consultations
194 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More