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.
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal.inria.fr/hal-01153540
Contributor : Michal Valko <>
Submitted on : Tuesday, May 19, 2015 - 11:33:08 PM
Last modification on : Friday, March 22, 2019 - 1:35:13 AM
Long-term archiving on : Thursday, April 20, 2017 - 4:23:57 AM

File

hanawal2015cheap.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01153540, version 1

Citation

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

Share

Metrics

Record views

415

Files downloads

142