Hüyük, A., W. R. Zame, and M. van der Schaar. “Inferring Lexicographically-Ordered Rewards from Preferences”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 5, June 2022, pp. 5737-45, doi:10.1609/aaai.v36i5.20516.