Grounded Action Transformation for Robot Learning in Simulation (2017)
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.
In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), San Francisco, CA, February 2017.

Slides (PDF)
Josiah Hanna Ph.D. Student jphanna [at] cs utexas edu
Peter Stone Faculty pstone [at] cs utexas edu