Summary: Regret Bounds for Gaussian Process Bandit Problems
Steffen Gr¨unew¨alder Jean-Yves Audibert Manfred Opper John Shawe-Taylor
University College London
steffen@cs.ucl.ac.uk
Universit´e Paris-Est
& INRIA/ENS/CNRS
audibert@imagine.enpc.fr
TU-Berlin
opperm@cs.tu-berlin.de
University College London
jst@cs.ucl.ac.uk
Abstract
Bandit algorithms are concerned with trad-
ing exploration with exploitation where a
number of options are available but we can
only learn their quality by experimenting
with them. We consider the scenario in which
the reward distribution for arms is modelled
by a Gaussian process and there is no noise
in the observed reward. Our main result is to

Source: Audibert, Jean-Yves - Département d'Informatique, École Normale Supérieure

Collections: Computer Technologies and Information Sciences