Learning from Observations Using a Single Video Demonstration and Human Feedback
Loading...
Links to Files
Permanent Link
Author/Creator
Author/Creator ORCID
Date
2019-09-29
Type of Work
Department
Program
Citation of Original Publication
Gandhi, 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/1909.13392
Rights
This 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.
Public Domain Mark 1.0
This 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.
Public Domain Mark 1.0
This 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.
Abstract
In 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.