Nie, Buqing, Jingtian Ji, Yangqing Fu, and Yue Gao. “Improve Robustness of Reinforcement Learning Against Observation Perturbations via l∞ Lipschitz Policy Networks”. Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 13 (March 24, 2024): 14457-14465. Accessed May 2, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/29360.