Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 DetailsÜbersicht
  Applying the Episodic Natural Actor-Critic Architecture to Motor Primitive Learning

Peters, J. (2007). Applying the Episodic Natural Actor-Critic Architecture to Motor Primitive Learning. In 15th European Symposium on Artificial Neural Networks (ESANN 2007) (pp. 295-300). Evere, Belgium: D-Side.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-CE15-3 Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-CE16-1
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Peters, J1, 2, Autor           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the “building blocks of movement generation”, called motor primitives. Motor primitives are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. We show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2007-04
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: URI: http://www.dice.ucl.ac.be/esann/proceedings/papers.php?ann=2007
BibTex Citekey: 4725
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 15th European Symposium on Artificial Neural Networks (ESANN 2007)
Veranstaltungsort: Brugge, Belgium
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 15th European Symposium on Artificial Neural Networks (ESANN 2007)
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Evere, Belgium : D-Side
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 295 - 300 Identifikator: -