Communication Dans Un Congrès Année : 2018

Thompson Sampling for the non-Stationary Corrupt Multi-Armed Bandit

Réda Alami
  • Fonction : Auteur
  • PersonId : 1654844
  • IdRef : 258036508

Résumé

We propose an extension of the corrupt multi-armed bandit problem proposed in Gajane et al. (2018) where the distributions of reward and feedback are non-stationary. We also propose an extension with three variants of the Global Switching Thompson Sampling proposed in Mellor and Shapiro (2013) for the corrupted setting. This extension is based on the aggregation of a growing number of experts seen as learners. Finally, we conduct experiments providing evidences that in practice our proposal compares favorably with the oracle that exactly knows the location of the environment changes.

Fichier principal
Vignette du fichier
PieceWiseCorruptedMAB.pdf (360.92 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-01963539 , version 1 (21-12-2018)

Licence

Identifiants

  • HAL Id : hal-01963539 , version 1

Citer

Réda Alami. Thompson Sampling for the non-Stationary Corrupt Multi-Armed Bandit. The 14th European Workshop on Reinforcement Learning, Oct 2018, Lille, France. ⟨hal-01963539⟩
133 Consultations
222 Téléchargements

Partager

  • More