Combinatorial Bandits Revisited - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Combinatorial Bandits Revisited

Résumé

This paper investigates stochastic and adversarial combinatorial multi-armed bandit problems. In the stochastic setting under semi-bandit feedback, we derive a problem-specific regret lower bound, and discuss its scaling with the dimension of the decision space. We propose ESCB, an algorithm that efficiently exploits the structure of the problem and provide a finite-time analysis of its regret. ESCB has better performance guarantees than existing algorithms, and significantly outperforms these algorithms in practice. In the adversarial setting under bandit feedback, we propose CombEXP, an algorithm with the same regret scaling as state-of-the-art algorithms, but with lower computational complexity for some combinatorial problems.
Fichier principal
Vignette du fichier
combes_combinatorial_bandits.pdf (753.99 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01257796 , version 1 (09-04-2020)

Identifiants

Citer

Richard Combes, Sadegh Talebi, Alexandre Proutière, Marc Lelarge. Combinatorial Bandits Revisited. NIPS 2015 - Twenty-ninth Conference on Neural Information Processing Systems, Dec 2015, Montreal, Canada. ⟨hal-01257796⟩
242 Consultations
236 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More