Cheap Bandits

Manjesh Kumar Hanawal 1 Venkatesh Saligrama 1 Michal Valko 2 Rémi Munos 2
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : We consider stochastic sequential learning problems where the learner can observe the average reward of several actions. Such a setting is interesting in many applications involving monitoring and surveillance, where the set of the actions to observe represent some (geographical) area. The importance of this setting is that in these applications , it is actually cheaper to observe average reward of a group of actions rather than the reward of a single action. We show that when the reward is smooth over a given graph representing the neighboring actions, we can maximize the cumulative reward of learning while minimizing the sensing cost. In this paper we propose CheapUCB, an algorithm that matches the regret guarantees of the known algorithms for this setting and at the same time guarantees a linear cost again over them. As a by-product of our analysis , we establish a ⌦(p dT) lower bound on the cumulative regret of spectral bandits for a class of graphs with effective dimension d.
Type de document :
Communication dans un congrès
International Conference on Machine Learning, 2015, Lille, France
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger
Contributeur : Michal Valko <>
Soumis le : mardi 19 mai 2015 - 23:33:08
Dernière modification le : mercredi 25 avril 2018 - 15:43:41
Document(s) archivé(s) le : jeudi 20 avril 2017 - 04:23:57


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01153540, version 1



Manjesh Kumar Hanawal, Venkatesh Saligrama, Michal Valko, Rémi Munos. Cheap Bandits. International Conference on Machine Learning, 2015, Lille, France. 〈hal-01153540〉



Consultations de la notice


Téléchargements de fichiers