2018-10-23-losey18a.md

title	abstract	keywords	layout	series	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	publisher	container-title	volume	genre	issued	pdf	extras
Including Uncertainty when Learning from Human Corrections	It is difficult for humans to efficiently teach robots how to correctly perform a task. One intuitive solution is for the robot to iteratively learn the human’s preferences from corrections, where the human improves the robot’s current behavior at each iteration. When learning from corrections, we argue that while the robot should estimate the most likely human preferences, it should also know what it does not know, and integrate this uncertainty as it makes decisions. We advance the state-of-the-art by introducing a Kalman filter for learning from corrections: this approach obtains the uncertainty of the estimated human preferences. Next, we demonstrate how the estimate uncertainty can be leveraged for active learning and risk-sensitive deployment. Our results indicate that obtaining and leveraging uncertainty leads to faster learning from human corrections.	human-robot interaction (HRI), inverse reinforcement learning (IRL)	inproceedings	Proceedings of Machine Learning Research	losey18a	0	Including Uncertainty when Learning from Human Corrections	123	132	123-132	123	false	Losey, Dylan P. and O'Malley, Marcia K.	given family Dylan P. Losey given family Marcia K. O’Malley	2018-10-23		PMLR	Proceedings of The 2nd Conference on Robot Learning	87	inproceedings	date-parts 2018 10 23	http://proceedings.mlr.press/v87/losey18a/losey18a.pdf