This paper presents a finite-time analysis of the KL-UCB algorithm, an online, horizon-free
index policy for stochastic bandit problems. We prove two distinct results: first, for arbitrary …

… of the UCB algorithm of Auer et al. [4]. For this modified algorithm we give an improved
bound on the regret with respect to the optimal reward. While for the original UCB algorithm the …

Better pharmacotherapies for epilepsy are needed for patients who are refractory to or have
tolerability difficulties with current treatments. Seletracetam, a new drug in epilepsy …

We study the stochastic contextual bandit problem, where the reward is generated from an
unknown function with additive noise. No assumption is made about the reward function other …

The paper proposes a novel upper confidence bound (UCB) procedure for identifying the arm
with the largest mean in a multi-armed bandit game in the fixed confidence setting using a …

… ucb LOS9 in the audiogenic seizure-prone mouse showed potent anticonvulsant activity. The
effects of ucb … the effects of the R enantiomcr, ucb LOhO, wcrc cvafuatcd in a Iimitcd range …

Discounted UCB … Discounted UCB … Discounted UCB …

… We extend the intuition of UCB algorithms to the RL setting. Using the outputs of the {Qk}
functions, we construct a UCB by adding the empirical standard deviation σ(st,a) of {Qk(st,a)}K …

… augmenting UCB transplants with ex vivo–expanded UCB cells is beneficial. … UCB units
and 1 patient receiving a related UCB graft. On day 0, 26 patients received unmanipulated UCB …

… In an open-label study, subjects with chronic liver disease were compared to healthy subjects
(UCB, data on file). The apparent total body clearance of brivaracetam was reduced by 24…