Optimizing Algorithms from Pairwise User Preferences

Typical black-box optimization approaches in robotics focus on learning from metric scores. However, that is not always possible, as not all developers have ground truth available. Learning appropriate robot behavior in human-centric contexts often requires querying users, who typically cannot provi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems S. 4161 - 4167
Hauptverfasser:	Keselman, Leonid, Shih, Katherine, Hebert, Martial, Steinfeld, Aaron
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.10.2023
Schlagworte:	Behavioral sciences Closed box Measurement Navigation Robot sensing systems Robustness Tuning
ISSN:	2153-0866
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!