BURNWAL, R.; BHATT, N. P.; RAVINDRAN, B. SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 24, p. 19790-19798, 2026. DOI: 10.1609/aaai.v40i24.39061. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39061. Acesso em: 28 apr. 2026.