Gu, S., Sel, B., Ding, Y., Wang, L., Lin, Q., Jin, M., & 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), 21099-21106. https://doi.org/10.1609/aaai.v38i19.30102