Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees
Safety is a critical component of autonomous systems and remains a challenge for learning-based policies to be utilized in the real world. How can we safely bridge this sim-to-real gap and certify the performance in actual deployment?
@article{hsuzen2022sim2lab2real,
title = {Sim-to-Lab-to-Real: Safe reinforcement learning with shielding and generalization guarantees},
journal = {Artificial Intelligence},
volume = {314},
pages = {103811},
year = {2023},
issn = {0004-3702},
doi = {https://doi.org/10.1016/j.artint.2022.103811},
url = {https://www.sciencedirect.com/science/article/pii/S0004370222001515},
author = {Kai-Chieh Hsu and Allen Z. Ren and Duy P. Nguyen and Anirudha Majumdar and Jaime F. Fisac},
keywords = {Reinforcement learning, Sim-to-Real transfer, Safety analysis, Generalization}}
Citation
Authors
Allen Z. Ren and Anirudha Majumdar were supported by the Toyota Research Institute (TRI), the NSF CAREER award [2044149], the Office of Naval Research [N00014-21-1-2803], and the School of Engineering and Applied Science at Princeton University through the generosity of William Addy ’82. This article solely reflects the opinions and conclusions of its authors and not ONR, NSF, TRI or any other Toyota entity. We would like to thank Zixu Zhang for his valuable advice on the setup of the physical experiments.