Back to reality for imitation learning
File(s)
Published version
OA Location
Author(s)
Johns, Edward
Type
Conference Paper
Abstract
Imitation learning, and robot learning in general, emerged due to breakthroughs in machine learning, rather than breakthroughs in robotics. As such, evaluation metrics for robot learning are deeply rooted in those for machine learning, and focus primarily on data efficiency. We believe that a better metric for real-world robot learning is time efficiency, which better models the true cost to humans. This is a call to arms to the robot learning community to develop our own evaluation metrics, tailored towards the long-term goals of real-world robotics.
Date Issued
2021-11-11
Date Acceptance
2021-09-14
Citation
2021, pp.1-5
Publisher
OpenReview
Start Page
1
End Page
5
Copyright Statement
© 2021 The Author(s).
Sponsor
Royal Academy of Engineering
Identifier
https://openreview.net/forum?id=QEG0rEN8uQS
Source
Conference on Robot Learning (CoRL) 2021
Publication Status
Published
Start Date
2021-11-08
Coverage Spatial
London, UK
Date Publish Online
2021-11-11