Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence

Abstract

We consider the problem of near-optimal arm identification in the fixed confidence setting of the infinitely armed bandit problem when nothing is known about the arm reservoir distribution. We (1) introduce a PAC-like framework within which to derive and cast results; (2) derive a sample complexity lower bound for near-optimal arm identification; (3) propose an algorithm that identifies a nearly-optimal arm with high probability and derive an upper bound on its sample complexity which is within a log factor of our lower bound; and (4) discuss whether our log^2(1/delta) dependence is inescapable for ``two-phase'' (select arms first, identify the best later) algorithms in the infinite setting. This work permits the application of bandit models to a broader class of problems where fewer assumptions hold.
Fichier principal
Vignette du fichier
aziz18.pdf (402.02 Ko) Télécharger le fichier
Loading...

Dates and versions

hal-01729969 , version 1 (12-03-2018)

Identifiers

Cite

Maryam Aziz, Jesse Anderton, Emilie Kaufmann, Javed Aslam. Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence. ALT 2018 - Algorithmic Learning Theory, Apr 2018, Lanzarote, Spain. ⟨hal-01729969⟩
202 View
264 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More