Yang Q, Simão TD, Tindemans SH, Spaan MTJ. WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning. AAAI [Internet]. 2021May18 [cited 2024May6];35(12):10639-46. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/17272