1. Policy gradients beyond ex-pectations: Conditional value-at-risk;tamar;ArXiv Preprint,2014
2. A comprehensive survey on safe rein-forcement learning;garcia;Journal of Machine Learning Research,2015
3. Dsac: distributional soft actor critic for risk-sensitive reinforcement learning;ma;ArXiv Preprint,2020
4. Distributional soft actor-critic: Off-policy reinforcement learning for addressing value estimation errors;duan;IEEE Transactions on Neural Networks and Learning Systems,2021
5. Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning