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

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

2012-04-02

arxiv.org/abs/1204.0416v1

Computer Science

Networking and Internet Architecture

No. RR-7917 (2012)

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and CCN Interest Forwarding Strategy as Multi-Armed Bandit Model with Delays will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-509792