A Note on KL-UCB+ Policy for the Stochastic Bandit
Machine Learning
2019-03-21 v2 Machine Learning
Abstract
A classic setting of the stochastic K-armed bandit problem is considered in this note. In this problem it has been known that KL-UCB policy achieves the asymptotically optimal regret bound and KL-UCB+ policy empirically performs better than the KL-UCB policy although the regret bound for the original form of the KL-UCB+ policy has been unknown. This note demonstrates that a simple proof of the asymptotic optimality of the KL-UCB+ policy can be given by the same technique as those used for analyses of other known policies.
Cite
@article{arxiv.1903.07839,
title = {A Note on KL-UCB+ Policy for the Stochastic Bandit},
author = {Junya Honda},
journal= {arXiv preprint arXiv:1903.07839},
year = {2019}
}
Comments
6 pages, corrected typos