Kevin G. Jamieson, Matthew Malloy, Robert Nowak, Sébastien Bubeck. lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits. In Maria-Florina Balcan, Csaba Szepesvári, editors, Proceedings of The 27th Conference on Learning Theory, COLT 2014, Barcelona, Spain, June 13-15, 2014. Volume 35 of JMLR Proceedings, pages 423-439, JMLR.org, 2014. [doi]
Abstract is missing.