Cheng, R., Orosz, G., Murray, R. M., & Burdick, J. W. (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), 3387-3395. https://doi.org/10.1609/aaai.v33i01.33013387