neural networks research group
areas
people
projects
demos
publications
software/data
Adversarial Imitation Learning from Video using a State Observer (2022)
Haresh Karnan and
Garrett Warnell
and
Faraz Torabi
and
Peter Stone
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.
View:
PDF
Citation:
In
International Conference on Robotics and Automation, 2022
, Philadelphia, Pennsylvania, May 2022.
Bibtex:
@inproceedings{ICRA22-karnan, title={Adversarial Imitation Learning from Video using a State Observer}, author={Haresh Karnan and Garrett Warnell and Faraz Torabi and Peter Stone}, booktitle={International Conference on Robotics and Automation, 2022}, month={May}, address={Philadelphia, Pennsylvania}, url="http://nn.cs.utexas.edu/?ICRA22-karnan", year={2022} }
People
Peter Stone
pstone [at] cs utexas edu
Faraz Torabi
faraztrb [at] cs utexas edu
Garrett Warnell
warnellg [at] cs utexas edu
Areas of Interest
Imitation Learning
Machine Learning
Robot Vision
Transfer Learning
Reinforcement Learning
Robotics