LUO, Jianing. Policy Gradient Methods for Multi-Agent Reinforcement Learning: A Comparative Study. Highlights in Science, Engineering and Technology, [S. l.], v. 140, p. 378–383, 2025. DOI: 10.54097/58j7ca95. Disponível em: https://hsetdata.com/index.php/ojs/article/view/752. Acesso em: 23 apr. 2026.