Representation Alignment from Human Feedback for Cross-Embodiment Reward Learning from Mixed-Quality Demonstrations

We study the problem of cross-embodiment inverse reinforcement learning, where we wish to learn a reward function from video demonstrations in one or more embodiments and then transfer the learned reward to a different embodiment (e.g., different action space, dynamics, size, shape, etc.). Learning...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-08
Hauptverfasser:	Mattson, Connor, Aribandi, Anurag, Brown, Daniel S
Format:	Artikel
Sprache:	eng
Schlagworte:	Alignment Feedback Representations Robots
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!