neural networks research group
areas
people
projects
demos
publications
software/data
Grounded Action Transformation for Robot Learning in Simulation (2017)
Josiah Hanna
and
Peter Stone
Robot learning in simulation is a promising alternative to the prohibitive sample cost of learning in the physical world. Unfortunately, policies learned in simulation often perform worse than hand-coded policies when applied on the physical robot. Grounded simulation learning (GSL) promises to address this issue by altering the simulator to better match the real world. This paper proposes a new algorithm for GSL -- Grounded Action Transformation -- and applies it to learning of humanoid bipedal locomotion. Our approach results in a 43.27% improvement in forward walk velocity compared to a state-of-the art hand-coded walk. We further evaluate our methodology in controlled experiments using a second, higher-fidelity simulator in place of the real world. Our results contribute to a deeper understanding of grounded simulation learning and demonstrate its effectiveness for learning robot control policies.
View:
PDF
,
HTML
Citation:
In
Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI)
, San Francisco, CA, February 2017.
Bibtex:
@inproceedings{AAAI17-Hanna, title={Grounded Action Transformation for Robot Learning in Simulation}, author={Josiah Hanna and Peter Stone}, booktitle={Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI)}, month={February}, address={San Francisco, CA}, url="http://nn.cs.utexas.edu/?hanna:aaai17", year={2017} }
Presentation:
Slides (PDF)
People
Josiah Hanna
jphanna [at] cs utexas edu
Peter Stone
pstone [at] cs utexas edu
Areas of Interest
Humanoid Robots