2023-12-02-datta23a.md

title	section	openreview	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisors	Poster	VtUZ4VGPns	Imitation learning has been applied to a range of robotic tasks, but can struggle when robots encounter edge cases that are not represented in the training data (i.e., distribution shift). Interactive fleet learning (IFL) mitigates distribution shift by allowing robots to access remote human supervisors during task execution and learn from them over time, but different supervisors may demonstrate the task in different ways. Recent work proposes Implicit Behavior Cloning (IBC), which is able to represent multimodal demonstrations using energy-based models (EBMs). In this work, we propose Implicit Interactive Fleet Learning (IIFL), an algorithm that builds on IBC for interactive imitation learning from multiple heterogeneous human supervisors. A key insight in IIFL is a novel approach for uncertainty quantification in EBMs using Jeffreys divergence. While IIFL is more computationally expensive than explicit methods, results suggest that IIFL achieves a 2.8x higher success rate in simulation experiments and a 4.5x higher return on human effort in a physical block pushing task over (Explicit) IFL, IBC, and other baselines.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	datta23a	0	IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisors	2340	2356	2340-2356	2340	false	Datta, Gaurav and Hoque, Ryan and Gu, Anrui and Solowjow, Eugen and Goldberg, Ken	given family Gaurav Datta given family Ryan Hoque given family Anrui Gu given family Eugen Solowjow given family Ken Goldberg	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/datta23a/datta23a.pdf