Gandhi, SunilOates, TimMohsenin, TinooshWaytowich, Nicholas2019-11-212019-11-212019-09-29Gandhi, 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/1909.13392http://hdl.handle.net/11603/16492In 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.8 pagesen-USThis 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 1.0This 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.video demonstrationshuman feedbackvisual representationstandard representationnumerical similarity ratingneural networkText