UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Generative Adversarial Imitation from Observation (2019)
Faraz Torabi
,
Garrett Warnell
, and
Peter Stone
Imitation from observation (IfO) is the problem of learning directly from state-only demonstrations without having access to the demonstrator's actions. The lack of action information both distinguishes IfO from most of the literature in imitation learning, and also sets it apart as a method that may enable agents to learn from a large set of previously inapplicable resources such as internet videos. In this paper, we propose both a general framework for IfO approaches and also a new IfO approach based on generative adversarial networks called generative adversarial imitation from observation (GAIfO). We conduct experiments in two different settings: (1) when demonstrations consist of low-dimensional, manually-defined state features, and (2) when demonstrations consist of high-dimensional, raw visual data. We demonstrate that our approach performs comparably to classical imitation learning approaches (which have access to the demonstrator's actions) and significantly outperforms existing imitation from observation methods in high-dimensional simulation environments.
View:
PDF
Citation:
Imitation, Intent, and Interaction (I3) Workshop at ICML 2019
(2019).
Bibtex:
@article{ICML19a-torabi, title={Generative Adversarial Imitation from Observation}, author={Faraz Torabi and Garrett Warnell and Peter Stone}, booktitle={Imitation, Intent, and Interaction (I3) Workshop at ICML 2019}, month={June}, address={Long Beach, California, USA}, url="http://www.cs.utexas.edu/users/ai-lab?ICML19a-torabi", year={2019} }
People
Peter Stone
Faculty
pstone [at] cs utexas edu
Faraz Torabi
Ph.D. Student
faraztrb [at] cs utexas edu
Garrett Warnell
Research Scientist
warnellg [at] cs utexas edu
Areas of Interest
Imitation Learning
Machine Learning
Labs
Learning Agents