Metcalf, Katherine, Miguel Sarabia, Masha Fedzechkina, and Barry-John Theobald. 2024. “Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It’s Complicated”. Proceedings of the AAAI Conference on Artificial Intelligence 38 (9):10128-36. https://doi.org/10.1609/aaai.v38i9.28877.