LOW, S. M.; KUMAR, A.; SANNER, S. Safe MDP Planning by Learning Temporal Patterns of Undesirable Trajectories and Averting Negative Side Effects. Proceedings of the International Conference on Automated Planning and Scheduling, [S. l.], v. 33, n. 1, p. 596-604, 2023. DOI: 10.1609/icaps.v33i1.27241. Disponível em: https://ojs.aaai.org/index.php/ICAPS/article/view/27241. Acesso em: 12 sep. 2024.