BOOTH, Serena; KNOX, W. Bradley; SHAH, Julie; NIEKUM, Scott; STONE, Peter; ALLIEVI, Alessandro. The Perils of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task Specifications. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 37, n. 5, p. 5920–5929, 2023. DOI: 10.1609/aaai.v37i5.25733. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/25733. Acesso em: 11 jul. 2026.