Groshev, E., M. Goldstein, A. Tamar, S. Srivastava, and P. Abbeel. “Learning Generalized Reactive Policies Using Deep Neural Networks”. Proceedings of the International Conference on Automated Planning and Scheduling, vol. 28, no. 1, June 2018, pp. 408-16, doi:10.1609/icaps.v28i1.13872.