Internal Regret with Partial Monitoring; Calibration-Based Optimal Algorithms - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2011

Internal Regret with Partial Monitoring; Calibration-Based Optimal Algorithms

Résumé

We provide consistent random algorithms for sequential decision under partial monitoring, \textsl{i.e.}\ when the decision maker does not observe the outcomes but receives instead random feedback signals. Those algorithms have no internal regret in the sense that, on the set of stages where the decision maker chose his action according to a given law, the average payoff could not have been improved in average by using any other fixed law. They are based on a generalization of calibration, no longer defined in terms of a Voronoï diagram but instead of a Laguerre diagram (a more general concept). This allows us to bound, for the first time in this general framework, the expected average internal -- as well as the usual external -- regret at stage $n$ by $O(n^{-1/3})$, which is known to be optimal.
Fichier principal
Vignette du fichier
algorithmHAL.pdf (324.7 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00567094 , version 1 (18-02-2011)

Identifiants

  • HAL Id : hal-00567094 , version 1

Citer

Vianney Perchet. Internal Regret with Partial Monitoring; Calibration-Based Optimal Algorithms. 2011. ⟨hal-00567094⟩
94 Consultations
42 Téléchargements

Partager

Gmail Facebook X LinkedIn More