Cheng, Richard, Gábor Orosz, Richard M. Murray, and Joel W. Burdick. 2019. “End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks”. Proceedings of the AAAI Conference on Artificial Intelligence 33 (01):3387-95. https://doi.org/10.1609/aaai.v33i01.33013387.