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...

Full description

Bibliographic Details

Published in:	Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems pp. 4161 - 4167
Main Authors:	Keselman, Leonid, Shih, Katherine, Hebert, Martial, Steinfeld, Aaron
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.10.2023
Subjects:	Behavioral sciences Closed box Measurement Navigation Robot sensing systems Robustness Tuning
ISSN:	2153-0866
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!