Nie, B., Ji, J., Fu, Y. and Gao, Y. 2024. Improve Robustness of Reinforcement Learning against Observation Perturbations via l∞ Lipschitz Policy Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 38, 13 (Mar. 2024), 14457-14465. DOI:https://doi.org/10.1609/aaai.v38i13.29360.