Nie, Buqing, Jingtian Ji, Yangqing Fu, and Yue Gao. 2024. “Improve Robustness of Reinforcement Learning Against Observation Perturbations via l∞ Lipschitz Policy Networks”. Proceedings of the AAAI Conference on Artificial Intelligence 38 (13):14457-65. https://doi.org/10.1609/aaai.v38i13.29360.