ZHANG, Matthew S.; ERDOGDU, Murat A; GARG, Animesh. Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 36, n. 8, p. 9066–9073, 2022. DOI: 10.1609/aaai.v36i8.20891. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/20891. Acesso em: 28 may. 2026.