Unconventional formats of background knowledge from human teacher in reward shaping

Raza, SA; Williams, MA

Unconventional formats of background knowledge from human teacher in reward shaping

Raza, SA

Williams, MA

Permalink

Publication Type:: Conference Proceeding
Citation:: ACM/IEEE International Conference on Human-Robot Interaction, 2017, pp. 373 - 374
Issue Date:: 2017-03-06

Closed Access

	Filename	Description	Size
	Unconventional Formats of Background Knowledge.pdf	Published version	747.51 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Raza, SA https://orcid.org/0000-0001-6570-4808	en_US
dc.contributor.author	Williams, MA https://orcid.org/0000-0002-1047-0503	en_US
dc.date.issued	2017-03-06	en_US
dc.identifier.citation	ACM/IEEE International Conference on Human-Robot Interaction, 2017, pp. 373 - 374	en_US
dc.identifier.isbn	9781450348850	en_US
dc.identifier.uri	http://hdl.handle.net/10453/126370
dc.description.abstract	© 2017 Authors. This research evaluates reward shaping with unconventional formats of human input. Conventionally, a human teacher is assumed to provide numeric rewards for complete task training. However, there are limitations to this conventional format. Firstly, the continuous demand of numeric rewards is onerous. Secondly, it is limited in extracting useful knowledge from humans. In this research, we have tested three unconventional formats of human input, two to increase social appeal of reward shaping and one to efficiently extraction knowledge from humans. The preliminary results on simulated domains validate the usefulness of these formats in terms of user's comfort and learning performance.	en_US
dc.relation.ispartof	ACM/IEEE International Conference on Human-Robot Interaction	en_US
dc.relation.isbasedon	10.1145/3029798.3034817	en_US
dc.title	Unconventional formats of background knowledge from human teacher in reward shaping	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2017 Authors. This research evaluates reward shaping with unconventional formats of human input. Conventionally, a human teacher is assumed to provide numeric rewards for complete task training. However, there are limitations to this conventional format. Firstly, the continuous demand of numeric rewards is onerous. Secondly, it is limited in extracting useful knowledge from humans. In this research, we have tested three unconventional formats of human input, two to increase social appeal of reward shaping and one to efficiently extraction knowledge from humans. The preliminary results on simulated domains validate the usefulness of these formats in terms of user's comfort and learning performance.

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

http://hdl.handle.net/10453/126370