Online Learning to Optimize Transmission over an Unknown Gilbert-Elliott Channel

Abstract : This paper studies the optimal transmission policy for a Gilbert-Elliott Channel. The transmitter has two actions: sending aggressively or sending conservatively, with rewards depending on the action chosen and the underlying channel state. The aim is to compute the scheduling policy to determine which actions to choose at each time slot in order to maximize the expected total discounted reward. We first establish the threshold structure of the optimal policy when the underlying channel statistics are known. We then consider the more challenging case when the statistics are unknown. For this problem, we map different threshold policies to arms of a suitably defined multiarmed bandit problem. To tractably handle the complexity introduced by countably infinite arms and the infinite time horizon, we weaken our objective a little: finding a (OPT ( + ))- approximate policy instead. We present the UCB-P algorithm, which can achieve this objective with logarithmic-time regret.
Type de document :
Communication dans un congrès
WiOpt'12: Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, May 2012, Paderborn, Germany. pp.27-32, 2012
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00763262
Contributeur : Service Ist Inria Sophia Antipolis-Méditerranée / I3s <>
Soumis le : lundi 10 décembre 2012 - 14:23:16
Dernière modification le : dimanche 17 décembre 2017 - 07:04:03
Document(s) archivé(s) le : lundi 11 mars 2013 - 12:31:26

Fichier

p27-wu.pdf
Accord explicite pour ce dépôt

Identifiants

  • HAL Id : hal-00763262, version 1

Collections

Citation

Yanting Wu, Bhaskar Krishnamachari. Online Learning to Optimize Transmission over an Unknown Gilbert-Elliott Channel. WiOpt'12: Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks, May 2012, Paderborn, Germany. pp.27-32, 2012. 〈hal-00763262〉

Partager

Métriques

Consultations de la notice

71

Téléchargements de fichiers

111