Learning from Observations Using a Single Video Demonstration and Human Feedback

Simple item page
dc.contributor.authorGandhi, Sunil
dc.contributor.authorOates, Tim
dc.contributor.authorMohsenin, Tinoosh
dc.contributor.authorWaytowich, Nicholas
dc.date.accessioned2019-11-21T17:41:27Z
dc.date.available2019-11-21T17:41:27Z
dc.date.issued2019-09-29
dc.description.abstractIn this paper, we present a method for learning from video demonstrations by using human feedback to construct a mapping between the standard representation of the agent and the visual representation of the demonstration. In this way, we leverage the advantages of both these representations, i.e., we learn the policy using standard state representations, but are able to specify the expected behavior using video demonstration. We train an autonomous agent using a single video demonstration and use human feedback (using numerical similarity rating) to map the standard representation to the visual representation with a neural network. We show the effectiveness of our method by teaching a hopper agent in the MuJoCo to perform a backflip using a single video demonstration generated in MuJoCo as well as from a real-world YouTube video of a person performing a backflip. Additionally, we show that our method can transfer to new tasks, such as hopping, with very little human feedback.en_US
dc.description.urihttps://arxiv.org/abs/1909.13392en_US
dc.format.extent8 pagesen_US
dc.genrejournal articles preprintsen_US
dc.identifierdoi:10.13016/m2hgsf-uvpt
dc.identifier.citationGandhi, Sunil; Oates, Tim; Mohsenin, Tinoosh; Waytowich, Nicholas; Learning from Observations Using a Single Video Demonstration and Human Feedback; Machine Learning (2019); https://arxiv.org/abs/1909.13392en_US
dc.identifier.urihttp://hdl.handle.net/11603/16492
dc.language.isoen_USen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Student Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.rightsPublic Domain Mark 1.0*
dc.rightsThis work was written as part of one of the author's official duties as an Employee of the United States Government and is therefore a work of the United States Government. In accordance with 17 U.S.C. 105, no copyright protection is available for such works under U.S. Law.
dc.rights.urihttp://creativecommons.org/publicdomain/mark/1.0/*
dc.subjectvideo demonstrationsen_US
dc.subjecthuman feedbacken_US
dc.subjectvisual representationen_US
dc.subjectstandard representationen_US
dc.subjectnumerical similarity ratingen_US
dc.subjectneural networken_US
dc.titleLearning from Observations Using a Single Video Demonstration and Human Feedbacken_US
dc.typeTexten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1909.13392.pdf
Size:
603.89 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection