GU, Shangding; SEL, Bilgehan; DING, Yuhao; WANG, Lu; LIN, Qingwei; JIN, Ming; KNOLL, Alois. Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 38, n. 19, p. 21099–21106, 2024. DOI: 10.1609/aaai.v38i19.30102. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/30102. Acesso em: 26 may. 2026.