A Neural Networks Committee for the Contextual Bandit Problem - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

A Neural Networks Committee for the Contextual Bandit Problem

Résumé

This paper presents a new contextual bandit algorithm, NeuralBandit, which does not need hypothesis on stationarity of contexts and rewards. Several neural networks are trained to modelize the value of rewards knowing the context. Two variants, based on multi-experts approach, are proposed to choose online the parameters of multi-layer perceptrons. The proposed algorithms are successfully tested on a large dataset with and without stationarity of rewards.
Fichier principal
Vignette du fichier
A Neural Networks Committee for the Contextual Bandit Problem.pdf (303.97 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01117311 , version 1 (16-02-2015)

Identifiants

Citer

Robin Allesiardo, Raphaël Féraud, Djallel Bouneffouf. A Neural Networks Committee for the Contextual Bandit Problem. The 21st International Conference on Neural Information Processing, Nov 2014, Kuching, Malaysia. pp.374 - 381, ⟨10.1007/978-3-319-12637-1_47⟩. ⟨hal-01117311⟩
253 Consultations
888 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More