Learning Robust Manipulation Skills with Guided Policy Search via Generative Motor Reflexes

Guided Policy Search enables robots to learn control policies for complex manipulation tasks efficiently. Therein, the control policies are represented as high-dimensional neural networks which derive robot actions based on states. However, due to the small number of real-world trajectory samples in...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-02
Hauptverfasser:	Ennen, Philipp, Bresenitz, Pia, Vossen, Rene, Hees, Frank
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer simulation Motors Neural networks Policies Reflexes Robot control Robots Robustness Searching Skills Task complexity Trajectories
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!