BONET, Blai; GEFFNER, Hector. Action Selection for MDPs: Anytime AO* Versus UCT. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 26, n. 1, p. 1749–1755, 2021. DOI: 10.1609/aaai.v26i1.8369. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/8369. Acesso em: 10 may. 2026.