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

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

Paul Ecoffet
  • Function : Author
  • PersonId : 1096041
Nicolas Fontbonne
Jean-Baptiste André
Nicolas Bredeche
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)

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⟩
39 View
71 Download

Share

Gmail Mastodon Facebook X LinkedIn More