A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences

Details A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences

2011-05-29

arxiv.org/abs/1105.5820v1

COLT'11 (2011) 18

Mathematics

Statistics Theory

Scientific paper

We consider a Kullback-Leibler-based algorithm for the stochastic multi-armed bandit problem in the case of distributions with finite supports (not necessarily known beforehand), whose asymptotic regret matches the lower bound of \cite{Burnetas96}. Our contribution is to provide a finite-time analysis of this algorithm; we get bounds whose main terms are smaller than the ones of previously known algorithms with finite-time analyses (like UCB-type algorithms).

Affiliated with

Also associated with

No associations

Rating

A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences 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 A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-290085