Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Use of variance estimation in the multi-armed bandit problem
 

Summary: Use of variance estimation in the multi-armed
bandit problem
Jean Yves Audibert
CERTIS - Ecole des Ponts
19, rue Alfred Nobel - Cit´e Descartes
77455 Marne-la-Vall´ee - France
audibert@certis.enpc.fr
R´emi Munos
INRIA Futurs, Grappa
Universit´e Lille 3, France
remi.munos@inria.fr
Csaba Szepesv´ari
Computer and Automation Research Institute
of the Hungarian Academy of Sciences
Kende u. 13-17, Budapest 1111, Hungary
szcsaba@sztaki.hu
Abstract
An important aspect of most decision making problems concerns the appro-
priate balance between exploitation (acting optimally according to the par-
tial knowledge acquired so far) and exploration of the environment (acting

  

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

 

Collections: Computer Technologies and Information Sciences