A Note on KL-UCB+ Policy for the Stochastic Bandit

2019/03/19 by Honda, Junya · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1903.07839

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.

Cited by

• Optimal Regret of Bernoulli Bandits under Global Differential Privacy

Related

• KL-UCB-switch: optimal regret bounds for stochastic bandits from both a\n distribution-dependent and a distribution-free viewpoints
• Regret lower bounds and extended Upper Confidence Bounds policies in stochastic multi-armed bandit problem
• Extended UCB Policies for Multi-armed Bandit Problems
• Robustness of Anytime Bandit Policies
• Bounded regret in stochastic multi-armed bandits