Hu, Tianmeng, and Biao Luo. “PA2D-MORL: Pareto Ascent Directional Decomposition Based Multi-Objective Reinforcement Learning”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 11, Mar. 2024, pp. 12547-55, doi:10.1609/aaai.v38i11.29148.