Optimization of Energy Policies Using Direct Value Search

Jérémie Decock 1, 2 Jean-Joseph Christophe 1, 2 Olivier Teytaud 1, 2
1 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : Direct Policy Search is a widely used tool for reinforcement learning; however, it is usually not suitable for handling high-dimensional constrained action spaces such as those arising in power system control (unit commitmen problems). We propose Direct Value Search, an hybridization of DPS with Bellman decomposition techniques. We prove runtime properties, and apply the results to an energy management problem.
Document type :
Documents associated with scientific events
Complete list of metadatas

https://hal.inria.fr/hal-00997562
Contributor : Jérémie Decock <>
Submitted on : Wednesday, June 4, 2014 - 11:54:07 PM
Last modification on : Thursday, April 5, 2018 - 12:30:12 PM
Long-term archiving on : Thursday, September 4, 2014 - 10:41:33 AM

File

slides.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00997562, version 1

Collections

Citation

Jérémie Decock, Jean-Joseph Christophe, Olivier Teytaud. Optimization of Energy Policies Using Direct Value Search. 9èmes Journées Francophones de Planification, Décision et Apprentissage (JFPDA'14), May 2014, Liège, Belgium. 2014. ⟨hal-00997562⟩

Share

Metrics

Record views

347

Files downloads

434