Wei, W., Y. Zhang, J. Liang, L. Li, and Y. Li. “Controlling Underestimation Bias in Reinforcement Learning via Quasi-Median Operation”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 8, June 2022, pp. 8621-8, doi:10.1609/aaai.v36i8.20840.