GODLEWSKI, Konrad; SAWICKI, Bartosz. Two-step reinforcement learning for multistage strategy card game. Bulletin of the Polish Academy of Sciences Technical Sciences, [S. l.], v. 72, n. 6, p. e151376, 2024. DOI: 10.24425/bpasts.2024.151376. Disponível em: https://wydawnictwo.pan.pl/index.php/bpasts/article/view/2407. Acesso em: 22 aug. 2026.