Gu, S., Sel, B., Ding, Y., Wang, L., Lin, Q., Jin, M. and Knoll, A. 2024. Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation. Proceedings of the AAAI Conference on Artificial Intelligence. 38, 19 (Mar. 2024), 21099-21106. DOI:https://doi.org/10.1609/aaai.v38i19.30102.