CCN interest forwarding strategy as Multi-Armed Bandit model with delays

Avrachenkov, Konstantin and Jacko, Peter (2012) CCN interest forwarding strategy as Multi-Armed Bandit model with delays. In: Network Games, Control and Optimization (NetGCooP), 2012 6th International Conference on. IEEE, FRA, pp. 38-43. ISBN 9781467360265

[img]
Preview
PDF (Netgcoop2012_IEEE_v7_submitted)
Netgcoop2012_IEEE_v7_submitted.pdf - Submitted Version

Download (250kB)

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 epsilon-greedy, tuned epsilon-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 epsilon-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 epsilon-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.

Item Type:
Contribution in Book/Report/Proceedings
Subjects:
ID Code:
71353
Deposited By:
Deposited On:
21 Oct 2014 12:33
Refereed?:
Yes
Published?:
Published
Last Modified:
22 Oct 2020 07:09