Skip to Main content Skip to Navigation
Conference papers

Learning for stochastic dynamic programming

Sylvain Gelly 1 Jérémie Mary 1 Olivier Teytaud 1
1 TANC - Algorithmic number theory for cryptology
Inria Saclay - Ile de France, LIX - Laboratoire d'informatique de l'École polytechnique [Palaiseau]
Abstract : We present experimental results about learning function values (i.e. Bellman values) in stochastic dynamic programming (SDP). All results come from openDP (, a freely available source code, and therefore can be reproduced. The goal is an independent comparison of learning methods in the framework of SDP.
Document type :
Conference papers
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download
Contributor : Sylvain Gelly <>
Submitted on : Thursday, November 9, 2006 - 5:06:02 PM
Last modification on : Thursday, December 3, 2020 - 4:56:02 PM
Long-term archiving on: : Thursday, September 20, 2012 - 2:35:23 PM


  • HAL Id : inria-00112796, version 1



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⟩



Record views


Files downloads