Predicting the consequence of action in digital control state spaces - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2016

Predicting the consequence of action in digital control state spaces

Résumé

The objective of this dissertation is to shed light on some fundamental impediments in learning control laws in continuous state spaces. In particular, if one wants to build artificial devices capable to learn motor tasks the same way they learn to classify signals and images, one needs to establish control rules that do not necessitate comparisons between quantities of the surrounding space. We propose, in that context, to take inspiration from the " end effector control " principle, as suggested by neuroscience studies, as opposed to the " displacement control " principle used in the classical control theory.
Fichier principal
Vignette du fichier
hdr-bb.pdf (214.98 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01374155 , version 1 (29-09-2016)

Licence

Paternité

Identifiants

  • HAL Id : hal-01374155 , version 1

Citer

Emmanuel Daucé. Predicting the consequence of action in digital control state spaces. 2016. ⟨hal-01374155⟩
196 Consultations
30 Téléchargements

Partager

Gmail Facebook X LinkedIn More