Reinforcement Learning with Rare Significant Events: Direct Policy Search vs. Gradient Policy Search - Sorbonne Université
Conference Papers Year : 2021

Reinforcement Learning with Rare Significant Events: Direct Policy Search vs. Gradient Policy Search

Paul Ecoffet
  • Function : Author
  • PersonId : 1096041
Sorbonne Université
Nicolas Fontbonne
Sorbonne Université
Jean-Baptiste André
Institut Jean-Nicod
Nicolas Bredeche
Sorbonne Université

Domains

Machine Learning [cs.LG] Artificial Intelligence [cs.AI] Neural and Evolutionary Computing [cs.NE]
Fichier principal
Vignette du fichier
2021 - PPOCMA_GECCO2021_poster_cameraReady_rc3_CAMREADY.pdf (460.78 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Nicolas Bredeche  : Connect in order to contact the contributor

https://hal.sorbonne-universite.fr/hal-03315728

Submitted on : Thursday, August 5, 2021-5:20:41 PM

Last modification on : Friday, April 19, 2024-4:18:55 PM

Long-term archiving on : Saturday, November 6, 2021-6:41:34 PM

Download

Dates and versions

hal-03315728 , version 1 (05-08-2021)

Identifiers

  • HAL Id : hal-03315728 , version 1

Cite

Paul Ecoffet, Nicolas Fontbonne, Jean-Baptiste André, Nicolas Bredeche. Reinforcement Learning with Rare Significant Events: Direct Policy Search vs. Gradient Policy Search. Genetic and Evolutionary Computation Conference Companion, 2021, Lille (en ligne), France. ⟨hal-03315728⟩

Export

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

ENS-PARIS CNRS CDF EHESS DEC PSL SORBONNE-UNIVERSITE JEAN-NICOD
44 View
84 Download

Share

More