Summary: '
&
$
%
NEAR-OPTIMAL REGRET BOUNDS FOR
REINFORCEMENT LEARNING
Peter Auer, Thomas Jaksch, Ronald Ortner
January 2009
University of Leoben
Chair of Information Technology
Technical Report No. CIT-2009-01
NEAR-OPTIMAL REGRET BOUNDS FOR
REINFORCEMENT LEARNING
Peter Auer, Thomas Jaksch, Ronald Ortner
University of Leoben
Chair of Information Technology
Franz Joseph Straße 18
A-8700 Leoben
Austria
www.unileoben.ac.at/~ infotech

Source: Auer, Peter - Department Mathematik und Informationstechnologie, Montanuniversität Leoben

Collections: Computer Technologies and Information Sciences