Reinforcement learning demonstrator for opportunistic spectrum access on real radio signals - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Reinforcement learning demonstrator for opportunistic spectrum access on real radio signals

Résumé

This demonstration presents a proof-of-concept for opportunistic spectrum access. It particularly focuses on reinforcement learning algorithm called UCB (Upper Confidence Bound) designed by the machine learning community to solve the MAB problem (Multi-Armed Bandit). The demonstrator shows the first worldwide implementation of reinforcement learning algorithms for OSA (opportunistic spectrum access) on real radio environment using USRP N210 platforms.

Domaines

Electronique
Fichier principal
Vignette du fichier
07343919.pdf (270.02 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01262063 , version 1 (04-02-2016)

Identifiants

Citer

Christophe Moy, Amor Nafkha, Malek Naoues. Reinforcement learning demonstrator for opportunistic spectrum access on real radio signals. 2015 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), Sep 2015, Stockholm, Sweden. ⟨10.1109/DySPAN.2015.7343919⟩. ⟨hal-01262063⟩
194 Consultations
485 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More