Cheap Bandits - Archive ouverte HAL Access content directly
Conference Papers Year :

Cheap Bandits

(1) , (1) , (2) , (2)
1
2

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.
Fichier principal
Vignette du fichier
hanawal2015cheap.pdf (2.05 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01153540 , version 1 (19-05-2015)

Identifiers

  • HAL Id : hal-01153540 , version 1

Cite

Manjesh Kumar Hanawal Hanawal, Venkatesh Saligrama, Michal Valko, Rémi Munos. Cheap Bandits. International Conference on Machine Learning, 2015, Lille, France. ⟨hal-01153540⟩
1587 View
90 Download

Share

Gmail Facebook Twitter LinkedIn More