Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Learning Motor Primitives with Reinforcement Learning

Peters, J., & Schaal, S. (2004). Learning Motor Primitives with Reinforcement Learning. Poster presented at 11th Joint Symposium on Neural Computation (JSNC 2004), Los Angeles, CA, USA.

Item is

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
https://resolver.caltech.edu/CaltechJSNC:2004.poster020 (Zusammenfassung)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Peters, J1, 2, Autor           
Schaal, S, Autor           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: One of the major challenges in action generation for robotics and in the understanding of human motor control is to learn the "building blocks of move- ment generation," or more precisely, motor primitives. Recently, Ijspeert et al. [1, 2] suggested a novel framework how to use nonlinear dynamical systems as motor primitives. While a lot of progress has been made in teaching these mo- tor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this poster, we evaluate different reinforcement learning approaches can be used in order to improve the performance of motor primitives. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and line out how these lead to a novel algorithm which is based on natural policy gradients [3]. We compare this algorithm to previous reinforcement learning algorithms in the context of dynamic motor primitive learning, and show that it outperforms these by at least an order of magnitude. We demonstrate the efficiency of the resulting reinforcement learning method for creating complex behaviors for automous robotics. The studied behaviors will include both discrete, finite tasks such as baseball swings, as well as complex rhythmic patterns as they occur in biped locomotion.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2004-05
 Publikationsstatus: Online veröffentlicht
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: 5066
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 11th Joint Symposium on Neural Computation (JSNC 2004)
Veranstaltungsort: Los Angeles, CA, USA
Start-/Enddatum: 2004-05-15

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle

einblenden: