UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Imitation Learning from Video by Leveraging Proprioception (2019)
Faraz Torabi
,
Garrett Warnell
, and
Peter Stone
Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected in the exact same environment and usually include the demonstrator's actions. Recently, however, the research community has begun to address some of these shortcomings by offering algorithmic solutions that enable imitation learning from observation (IfO), e.g., learning to perform a task from visual demonstrations that may be in a different environment and do not include actions. Motivated by the fact that agents often also have access to their own internal states (i.e., proprioception), we propose and study an IfO algorithm that leverages this information in the policy learning process. The proposed architecture learns policies over proprioceptive state representations and compares the resulting trajectories visually to the demonstration data. We experimentally test the proposed technique on several MuJoCo domains and show that it outperforms other imitation from observation algorithms by a large margin.
View:
PDF
Citation:
In
Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI)
, Macao, China, August 2019.
Bibtex:
@inproceedings{IJCAI19b-torabi, title={Imitation Learning from Video by Leveraging Proprioception}, author={Faraz Torabi and Garrett Warnell and Peter Stone}, booktitle={Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI)}, month={August}, address={Macao, China}, url="http://www.cs.utexas.edu/users/ai-lab?IJCAI19b-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