Combinatorial Bandits Revisited

Abstract : 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.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01257796
Contributeur : Richard Combes <>
Soumis le : lundi 18 janvier 2016 - 11:54:09
Dernière modification le : jeudi 22 novembre 2018 - 14:32:59

Lien texte intégral

Identifiants

  • HAL Id : hal-01257796, version 1
  • ARXIV : 1502.03475

Citation

Richard Combes, Sadegh Talebi, Alexandre Proutière, Marc Lelarge. Combinatorial Bandits Revisited. NIPS, 2015, Montreal, Canada. NIPS. 〈hal-01257796〉

Partager

Métriques

Consultations de la notice

450