Dynamic Action Masking and Priority Experience Replay in Deep Reinforcement Learning News Recommenders. Journal of Systems Engineering and Information Technology (JOSEIT), [S. l.], v. 4, n. 3, p. 103–107, 2025. DOI: 10.29207/7jqyxp41. Disponível em: https://jurnal.iaii.or.id/index.php/JOSEIT/article/view/8555. Acesso em: 30 oct. 2026.