LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : ``Simple regret'' algorithms are designed for noisy optimization in unstructured domains. In particular, this literature has shown that the uniform algorithm is indeed optimal asymptotically and suboptimal non-asymptotically. We investigate theoretically and experimentally the application of these algorithms, for automatic parameter tuning, in particular from the point of view of the number of samples required for ``uniform'' to be relevant and from the point of view of statistical guarantees. We see that for moderate numbers of arms, the possible improvement in terms of computational power required for statistical validation can't be more than linear as a function of the number of arms and provide a simple rule to check if the simple uniform algorithm (trivially parallel) is relevant. Our experiments are performed on the tuning of a Monte-Carlo Tree Search algorithm, a great recent tool for high-dimensional planning with particularly impressive results for difficult games and in particular the game of Go.
https://hal.inria.fr/inria-00467796
Contributor : Olivier Teytaud
<>
Submitted on : Tuesday, March 30, 2010 - 3:03:25 PM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Document(s) archivé(s) le : Thursday, June 30, 2011 - 11:17:48 AM
