UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Reinforced Grounded Action Transformation for Sim-to-Real Transfer (2020)
Haresh Karnan, Siddharth Desai,
Josiah P. Hanna
,
Garrett Warnell
, and
Peter Stone
Robots can learn to do complex tasks in simulation, but often, learned behaviors fail to transfer well to the real world due to simulator imperfections (the “reality gap”). Some existing solutions to this sim-to-real problem, such as Grounded Action Transformation (GAT), use a small amount of real world experience to minimize the reality gap by “grounding” the simulator. While very effective in certain scenarios, GAT is not robust on problems that use complex function approximation techniques to model a policy. In this paper, we introduce Reinforced Grounded Action Transformation (RGAT), a new sim-to-real technique that uses Reinforcement Learning (RL) not only to update the target policy in simulation, but also to perform the grounding step itself. This novel formulation allows for end-to-end training during the grounding step, which, compared to GAT, produces a better grounded simulator. Moreover, we show experimentally in several MuJoCo domains that our approach leads to successful transfer for policies modeled using neural networks
View:
PDF
Citation:
In
IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS 2020)
, October 2020.
Bibtex:
@inproceedings{IROS20-Karnan, title={Reinforced Grounded Action Transformation for Sim-to-Real Transfer}, author={Haresh Karnan and Siddharth Desai and Josiah P. Hanna and Garrett Warnell and Peter Stone}, booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS 2020)}, month={October}, url="http://www.cs.utexas.edu/users/ai-lab?IROS20-Karnan", year={2020} }
People
Josiah Hanna
Ph.D. Student
jphanna [at] cs utexas edu
Peter Stone
Faculty
pstone [at] cs utexas edu
Garrett Warnell
Research Scientist
warnellg [at] cs utexas edu
Areas of Interest
Machine Learning
Reinforcement Learning
Robotics
Transfer Learning
Labs
Learning Agents