KORKMAZ, E. Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 27, p. 22662-22670, 2026. DOI: 10.1609/aaai.v40i27.39427. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39427. Acesso em: 25 apr. 2026.