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
Conference Papers 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, commonly reported as the best currently available algorithm. We prove the uniform logarithmic bound for the tuned $\eps$-greedy algorithm in the presence of delays. 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.
No file

Dates and versions

hal-00764011 , version 1 (12-12-2012)

Identifiers

  • HAL Id : hal-00764011 , version 1

Cite

Konstantin Avrachenkov, Peter Jacko. CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays. NetGCoop'12: The 6th International Conference on Network Games, Control and Optimization, Nov 2012, Avignon, France. ⟨hal-00764011⟩

Collections

INRIA INRIA2
55 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More