Faster Rates for Policy Learning - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2017

Faster Rates for Policy Learning

Résumé

This article improves the existing proven rates of regret decay in optimal policy estimation. We give a margin-free result showing that the regret decay for estimating a within-class optimal policy is second-order for empirical risk minimizers over Donsker classes, with regret decaying at a faster rate than the standard error of an efficient estimator of the value of an optimal policy. We also give a result from the classification literature that shows that faster regret decay is possible via plug-in estimation provided a margin condition holds. Four examples are considered. In these examples, the regret is expressed in terms of either the mean value or the median value; the number of possible actions is either two or finitely many; and the sampling scheme is either independent and identically distributed or sequential, where the latter represents a contextual bandit sampling scheme.
Fichier principal
Vignette du fichier
fasterRatesForPolicyLearning.pdf (372.32 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01511409 , version 1 (20-04-2017)

Identifiants

Citer

Alexander R Luedtke, Antoine Chambaz. Faster Rates for Policy Learning. 2017. ⟨hal-01511409⟩

Relations

267 Consultations
84 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More