A Contextual Bandit Bake-off - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

A Contextual Bandit Bake-off

Résumé

Contextual bandit algorithms are essential for solving many real-world interactive machine learning problems. Despite multiple recent successes on statistically and computationally efficient methods, the practical behavior of these algorithms is still poorly understood. We leverage the availability of large numbers of supervised learning datasets to compare and empirically optimize contextual bandit algorithms, focusing on practical methods that learn by relying on optimization oracles from supervised learning. We find that a recent method (Foster et al., 2018) using optimism under uncertainty works the best overall. A surprisingly close second is a simple greedy baseline that only explores implicitly through the diversity of contexts, followed by a variant of Online Cover (Agarwal et al., 2014) which tends to be more conservative but robust to problem specification by design. Along the way, we also evaluate and improve several internal components of contextual bandit algorithm design. Overall, this is a thorough study and review of contextual bandit methodology.
Fichier principal
Vignette du fichier
main.pdf (738.34 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01708310 , version 1 (13-02-2018)
hal-01708310 , version 2 (30-05-2018)
hal-01708310 , version 3 (26-12-2018)
hal-01708310 , version 4 (24-06-2021)

Identifiants

Citer

Alberto Bietti, Alekh Agarwal, John Langford. A Contextual Bandit Bake-off. 2018. ⟨hal-01708310v3⟩
669 Consultations
2501 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More