Combinatorial semi-bandit with known covariance - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Combinatorial semi-bandit with known covariance

Abstract

The combinatorial stochastic semi-bandit problem is an extension of the classical multi-armed bandit problem in which an algorithm pulls more than one arm at each stage and the rewards of all pulled arms are revealed. One difference with the single arm variant is that the dependency structure of the arms is crucial. Previous works on this setting either used a worst-case approach or imposed independence of the arms. We introduce a way to quantify the dependency structure of the problem and design an algorithm that adapts to it. The algorithm is based on linear regression and the analysis develops techniques from the linear bandit literature. By comparing its performance to a new lower bound, we prove that it is optimal, up to a poly-logarithmic factor in the number of pulled arms.
Fichier principal
Vignette du fichier
ols_ucb_ArXiv.pdf (554.86 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01408534 , version 1 (05-12-2016)

Identifiers

Cite

Rémy Degenne, Vianney Perchet. Combinatorial semi-bandit with known covariance. NIPS 2016 (Conference on Neural Information Processing Systems), Dec 2016, Barcelona, Spain. ⟨hal-01408534⟩
46 View
94 Download

Altmetric

Share

Gmail Facebook X LinkedIn More