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), pp. 21099-21106. doi: 10.1609/aaai.v38i19.30102.