Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
Jean-Yves Audibert, Rémi Munos, and Csaba Szepesvári, 2009
Download
Abstract
(unavailable)
BibTeX Entry
@Article{Audibert+MS:2009,
author = "Audibert, Jean-Yves and Munos, R{\'e}mi and Szepesv{\'a}ri, Csaba",
title = "Exploration-exploitation tradeoff using variance estimates in multi-armed bandits",
journal = "Theoretical Computer Science",
year = "2009",
volume = "410",
number = "19",
pages = "1876--1902",
url = "http://www.ualberta.ca/~szepesva/papers/ucbtuned-journal.pdf",
bib2html_rescat = "Bandits",
}