METCALF, Katherine; SARABIA, Miguel; FEDZECHKINA, Masha; THEOBALD, Barry-John. Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It’s Complicated. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 38, n. 9, p. 10128–10136, 2024. DOI: 10.1609/aaai.v38i9.28877. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/28877. Acesso em: 19 may. 2026.