Metcalf, K. et al. 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 (Mar. 2024), 10128–10136. DOI:https://doi.org/10.1609/aaai.v38i9.28877.