Delgrange, Florent, et al. “Distillation of RL Policies With Formal Guarantees via Variational Abstraction of Markov Decision Processes”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 6, June 2022, pp. 6497-05, doi:10.1609/aaai.v36i6.20602.