Explaining Imitation Learning Through Frames

Zheng, B; Zhou, J; Liu, C; Li, Y; Chen, F

Explaining Imitation Learning Through Frames

Zheng, B

Zhou, J Liu, C Li, Y Chen, F

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Intelligent Systems, 2024, PP, (99), pp. 1-9
Issue Date:: 2024-01-01

Embargoed

	Filename	Description	Size
	Explaining Imitation Learning Through Frames.pdf	Accepted version	1.19 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 24 May 2026

Full metadata record

Field	Value	Language
dc.contributor.author	Zheng, B https://orcid.org/0000-0003-1223-9230
dc.contributor.author	Zhou, J
dc.contributor.author	Liu, C
dc.contributor.author	Li, Y
dc.contributor.author	Chen, F
dc.date.accessioned	2024-06-20T01:41:21Z
dc.date.available	2024-06-20T01:41:21Z
dc.date.issued	2024-01-01
dc.identifier.citation	IEEE Intelligent Systems, 2024, PP, (99), pp. 1-9
dc.identifier.issn	1541-1672
dc.identifier.issn	1941-1294
dc.identifier.uri	http://hdl.handle.net/10453/179588
dc.description.abstract	As one of the prevalent methods to achieve automation systems, Imitation Learning (IL) presents a promising performance in a wide range of domains. However, despite the considerable improvement in policy performance, the corresponding research on the explainability of IL models is still limited. Inspired by the recent approaches in explainable artificial intelligence, we proposed a model-agnostic explaining framework for IL models called R2RISE. R2RISE aims to explain the importance of frames with respect to the overall policy performance. It iteratively retrains the black-box IL model from the randomized masked demonstrations and uses the conventional evaluation outcome environment returns as the coefficient to build an importance map. We also conducted experiments to investigate three major questions concerning frames’ importance equality, the effectiveness of the importance map, and connections in importance maps from different IL models. The result shows that R2RISE distinguishes important frames from the demonstrations effectively.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation.ispartof	IEEE Intelligent Systems
dc.relation.isbasedon	10.1109/MIS.2024.3404988
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0806 Information Systems, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	40 Engineering
dc.subject.classification	46 Information and computing sciences
dc.title	Explaining Imitation Learning Through Frames
dc.type	Journal Article
utslib.citation.volume	PP
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0806 Information Systems
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2026-05-24T00:00:00+1000Z
dc.date.updated	2024-06-20T01:41:20Z
pubs.issue	99
pubs.publication-status	Published
pubs.volume	PP
utslib.citation.issue	99

Abstract:

As one of the prevalent methods to achieve automation systems, Imitation Learning (IL) presents a promising performance in a wide range of domains. However, despite the considerable improvement in policy performance, the corresponding research on the explainability of IL models is still limited. Inspired by the recent approaches in explainable artificial intelligence, we proposed a model-agnostic explaining framework for IL models called R2RISE. R2RISE aims to explain the importance of frames with respect to the overall policy performance. It iteratively retrains the black-box IL model from the randomized masked demonstrations and uses the conventional evaluation outcome environment returns as the coefficient to build an importance map. We also conducted experiments to investigate three major questions concerning frames’ importance equality, the effectiveness of the importance map, and connections in importance maps from different IL models. The result shows that R2RISE distinguishes important frames from the demonstrations effectively.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/179588