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
Aug 2, 2011 3393 views 
en-de
en-es
en-fr
en-sl
en
en-zh
en-pt
0.25
0.5
0.75
1.25
1.5
1.75
2
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 Burnetas and Katehakis (1996). 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).