Practical Evaluation and Optimization of Contextual Bandit Algorithms - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Practical Evaluation and Optimization of Contextual Bandit Algorithms

Résumé

We study and empirically optimize contextual bandit learning, exploration, and problem encodings across 500+ datasets, creating a reference for practitioners and discovering or reinforcing a number of natural open problems for researchers. Across these experiments we show that minimizing the amount of exploration is a key design goal for practical performance. Remarkably, many problems can be solved purely via the implicit exploration imposed by the diversity of contexts. For practitioners, we introduce a number of practical improvements to common exploration algorithms including Bootstrap Thompson sampling, Online Cover, and $\epsilon$-greedy. We also detail a new form of reduction to regression for learning from exploration data. Overall, this is a thorough study and review of contextual bandit methodology.
Fichier principal
Vignette du fichier
practical_cb.pdf (2.76 Mo) 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. Practical Evaluation and Optimization of Contextual Bandit Algorithms. 2018. ⟨hal-01708310v1⟩
669 Consultations
2494 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More