Gu S, Sel B, Ding Y, Wang L, Lin Q, Jin M, Knoll A. Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation. AAAI [Internet]. 2024Mar.24 [cited 2024May17];38(19):21099-106. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/30102