CHENG, Richard; OROSZ, Gábor; MURRAY, Richard M.; BURDICK, Joel W. End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 33, n. 01, p. 3387–3395, 2019. DOI: 10.1609/aaai.v33i01.33013387. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/4213. Acesso em: 25 may. 2026.