• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Adversarial Imitation Learning from Video using a State Observer.
Haresh
Karnan, Garrett Warnell, Faraz
Torabi, and Peter Stone.
In International Conference on Robotics
and Automation, 2022, May 2022.
Video
The imitation learning research community has recently made significant progress towards the goal of enabling artificial agents to imitate behaviors from video demonstrations alone. However, current state-of-the-art approaches developed for this problem exhibit high sample complexity due, in part, to the high-dimensional nature of video observations. Towards addressing this issue, we introduce here a new algorithm called Visual Generative Adversarial Imitation from Observation using a State Observer VGAIfO-SO. At its core, VGAIfO-SO seeks to address sample inefficiency using a novel, self-supervised state observer, which provides estimates of lower-dimensional proprioceptive state representations from high-dimensional images. We show experimentally in several continuous control environments that VGAIfO-SO is more sample efficient than other IfO algorithms at learning from video-only demonstrations and can sometimes even achieve performance close to the Generative Adversarial Imitation from Observation (GAIfO) algorithm that has privileged access to the demonstrator's proprioceptive state information.
@InProceedings{ICRA22-karnan,
author = {Haresh Karnan and Garrett Warnell and Faraz Torabi and Peter Stone},
title = {Adversarial Imitation Learning from Video using a State Observer},
booktitle = {International Conference on Robotics and Automation, 2022},
location = {Online},
month = {May},
year = {2022},
abstract = {The imitation learning research community has recently made significant progress towards the goal of enabling artificial agents to imitate behaviors from video demonstrations alone. However, current state-of-the-art approaches developed for this problem exhibit high sample complexity due, in part, to the high-dimensional nature of video observations. Towards addressing this issue, we introduce here a new algorithm called Visual Generative Adversarial Imitation from Observation using a State Observer VGAIfO-SO. At its core, VGAIfO-SO seeks to address sample inefficiency using a novel, self-supervised state observer, which provides estimates of lower-dimensional proprioceptive state representations from high-dimensional images. We show experimentally in several continuous control environments that VGAIfO-SO is more sample efficient than other IfO algorithms at learning from video-only demonstrations and can sometimes even achieve performance close to the Generative Adversarial Imitation from Observation (GAIfO) algorithm that has privileged access to the demonstrator's proprioceptive state information.},
wwwnote={<a href="https://www.youtube.com/watch?v=q21OCKJPXNo&ab_channel=Hareshkarnan">Video</a>}
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 17, 2024 18:42:51