@inproceedings{8fe565acd0f041ba9c85e7cfa4d9aaba,
title = "Grounded Action Transformation for Robot Learning in Simulation",
abstract = "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.",
keywords = "Grounded simulation learning, Robotic bipedal walking, Transfer from simulation",
author = "Josiah Hanna and Peter Stone",
year = "2017",
month = feb,
day = "12",
language = "English",
isbn = "978-1-57735-784-1",
volume = "5",
series = "Proceedings of the AAAI Conference on Artificial Intelligence",
publisher = "AAAI Press",
pages = "3834--3840",
booktitle = "Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17)",
note = "Thirty-First AAAI Conference on Artificial Intelligence, AAAI 2017 ; Conference date: 04-02-2017 Through 09-02-2017",
}