Services
- Same authors
-
Related articles
- Recommend this article
- Download citation
- Alert me when this article is cited
- Alert me when this article is corrected
|
ESAIM: P&S, October 2005, Vol. 9, pp. 277-282
DOI: 10.1051/ps:2005017
A two armed bandit type problem revisited
Gilles PagèsLaboratoire de Probabilités et Modèles Aléatoires, UMR 7599, Université Paris 6, case 188, 4, place Jussieu, 75252 Paris Cedex 5, France; gpa@ccr.jussieu.fr
(Received December 10, 2004. Revised April 29, 2005.)
Abstract
In Benaïm and Ben Arous (2003) is solved a multi-armed
bandit problem arising in the theory of learning in games. We propose
a short and elementary proof of this result based on a variant of
the Kronecker lemma.
Mathematics Subject Classification. 91A20, 91A12, 60F99.
Key words: Two-armed bandit problem, Kronecker lemma, learning theory, stochastic fictitious play.
© EDP Sciences, SMAI 2005
| What is OpenURL? |



Document
BibSonomy
CiteUlike
Connotea
Del.icio.us
Digg
Facebook