CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2012

CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays

Peter Jacko
  • Function : Author
  • PersonId : 923125

Abstract

We consider Content Centric Network (CCN) interest forwarding problem as a Multi-Armed Bandit (MAB) problem with delays. We investigate the transient behaviour of the $\eps$-greedy, tuned $\eps$-greedy and Upper Confidence Bound (UCB) interest forwarding policies. Surprisingly, for all the three policies very short initial exploratory phase is needed. We demonstrate that the tuned $\eps$-greedy algorithm is nearly as good as the UCB algorithm, the best currently available algorithm. We prove the uniform logarithmic bound for the tuned $\eps$-greedy algorithm. In addition to its immediate application to CCN interest forwarding, the new theoretical results for MAB problem with delays represent significant theoretical advances in machine learning discipline.
Fichier principal
Vignette du fichier
RR-7917.pdf (359.52 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00683827 , version 1 (29-03-2012)
hal-00683827 , version 2 (01-04-2012)

Identifiers

Cite

Konstantin Avrachenkov, Peter Jacko. CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays. [Research Report] RR-7917, INRIA. 2012. ⟨hal-00683827v2⟩
184 View
263 Download

Altmetric

Share

Gmail Facebook X LinkedIn More