Learning for stochastic dynamic programming - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

Learning for stochastic dynamic programming

Sylvain Gelly
  • Function : Author
  • PersonId : 836546
Algorithmic number theory for cryptology
Jérémie Mary
Algorithmic number theory for cryptology
Olivier Teytaud
Algorithmic number theory for cryptology
CV

Abstract

We present experimental results about learning function values (i.e. Bellman values) in stochastic dynamic programming (SDP). All results come from openDP (opendp.sourceforge.net), a freely available source code, and therefore can be reproduced. The goal is an independent comparison of learning methods in the framework of SDP.

Domains

Machine Learning [cs.LG]
Fichier principal
Vignette du fichier
lfordp.pdf (99.33 Ko) Télécharger le fichier

Sylvain Gelly  : Connect in order to contact the contributor

https://inria.hal.science/inria-00112796

Submitted on : Thursday, November 9, 2006-5:06:02 PM

Last modification on : Friday, March 24, 2023-2:52:48 PM

Long-term archiving on: Thursday, September 20, 2012-2:35:23 PM

Download

Dates and versions

inria-00112796 , version 1 (09-11-2006)

Identifiers

  • HAL Id : inria-00112796 , version 1

Cite

Sylvain Gelly, Jérémie Mary, Olivier Teytaud. Learning for stochastic dynamic programming. 11th European Symposium on Artificial Neural Networks (ESANN), Apr 2006, bruges Belgium. ⟨inria-00112796⟩

Export

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

X CNRS INRIA LIX X-LIX X-DEP-INFO PARISTECH INRIA2
253 View
322 Download

Share

Gmail Facebook X LinkedIn More