UCB revisited: Improved regret bounds for the stochastic multi-armed bandit problem

ISSN： 0031-5303

Source： Periodica Mathematica Hungarica, Vol.61, Iss.1-2, 2010-09, pp. : 55-65

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

Related content

Multi-armed bandits with episode context

By Rosin Christopher

Annals of Mathematics and Artificial Intelligence, Vol. 61, Iss. 3, 2011-03 ,pp. : 203-230

Springer Publishing Company

Access to resources Recommend Favorite

A Multi-armed Neutral Receptor for ,&ohgr;-Dicarboxylate Anions

By Zeng Zhen-Ya He Yong-Bing Wu Jin-Long Wei Lan-Hua Liu Shun-Ying Huang Yan-Yan Meng Ling-Zhi Hu Ling

Supramolecular Chemistry, Vol. 16, Iss. 4, 2004-06 ,pp. : 233-238

Taylor & Francis Ltd

Access to resources Recommend Favorite

Improved lower bounds for the capacitated lot sizing problem with setup times

By Jans R. Degraeve Z.

Operations Research Letters, Vol. 32, Iss. 2, 2004-03 ,pp. : 185-195

Elsevier

Access to resources Recommend Favorite

Upper and Lower Bounds of a Solution of the Cauchy Problem for a Stochastic Differential Equation of Parabolic Type with Power Nonlinearities (Weak Source)

By Mel'nik S.A.

Ukrainian Mathematical Journal, Vol. 54, Iss. 1, 2002-01 ,pp. : 76-84

Springer Publishing Company

Access to resources Recommend Favorite

Stochastic Bounds for the Sparre Andersen Process

By Pellerey Franco Zucca Cristina

Methodology And Computing In Applied Probability, Vol. 7, Iss. 2, 2005-06 ,pp. : 225-247

Springer Publishing Company

Access to resources Recommend Favorite