HU, Tianmeng; LUO, Biao. PA2D-MORL: Pareto Ascent Directional Decomposition Based Multi-Objective Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 38, n. 11, p. 12547–12555, 2024. DOI: 10.1609/aaai.v38i11.29148. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/29148. Acesso em: 14 may. 2026.