YANG, C.; LITTMAN, M.; CARBIN, M. Computably Continuous Reinforcement-Learning Objectives Are PAC-Learnable. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 37, n. 9, p. 10729-10736, 2023. DOI: 10.1609/aaai.v37i9.26273. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/26273. Acesso em: 21 may. 2024.