Liotet, P., F. Vidaich, A. M. Metelli, and M. Restelli. “Lifelong Hyper-Policy Optimization With Multiple Importance Sampling Regularization”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 7, June 2022, pp. 7525-33, doi:10.1609/aaai.v36i7.20717.