Inverse Constraint Learning and Generalization by Transferable Reward Decomposition

We present the problem of inverse constraint learning (ICL), which recovers constraints from demonstrations to autonomously reproduce constrained skills in new scenarios. However, ICL suffers from an ill-posed nature, leading to inaccurate inference of constraints from demonstrations. To figure it o...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE robotics and automation letters 2024-01, Vol.9 (1), p.279-286
Hauptverfasser:	Jang, Jaehwi, Song, Minjae, Park, Daehyung
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Behavioral sciences constrained motion planning Constraints Costs Decomposition Learning from demonstration Linear programming Machine learning Optimization Skills Task analysis Training Trajectory
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!