Generalizable Imitation Learning Through Pre-Trained Representations

In this paper we leverage self-supervised vision transformer models and their emergent semantic abilities to improve the generalization abilities of imitation learning policies. We introduce BC-ViT, an imitation learning algorithm that leverages rich DINO pre-trained Visual Transformer (ViT) patch-l...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Chang, Wei-Di, Hogan, Francois, Meger, David, Dudek, Gregory
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Robotics
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!