Skip to Main content Skip to Navigation
Journal articles

A penalized bandit algorithm

Abstract : We study a two armed-bandit algorithm with penalty. We show the convergence of the algorithm and establish the rate of convergence. For some choices of the parameters, we obtain a central limit theorem in which the limit distribution is characterized as the unique stationary distribution of a discontinuous Markov process.
Document type :
Journal articles
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00012187
Contributor : Gilles Pagès <>
Submitted on : Tuesday, October 18, 2005 - 5:57:56 PM
Last modification on : Thursday, December 10, 2020 - 10:49:32 AM
Long-term archiving on: : Thursday, April 1, 2010 - 10:47:25 PM

Identifiers

Citation

Damien Lamberton, Gilles Pagès. A penalized bandit algorithm. Electronic Journal of Probability, Institute of Mathematical Statistics (IMS), 2008, 13, 341-373 ; http://dx.doi.org/10.1214/EJP.v13-489. ⟨10.1214/EJP.v13-489⟩. ⟨hal-00012187⟩

Share

Metrics

Record views

656

Files downloads

1208