AGARWAL, P.; WAJID, M. S.; KALYANAKRISHNAN, S. An Improved Lower Bound on the Length of Locally-Improving Policy Sequences in MDPs with Large Action Sets. Proceedings of the International Conference on Automated Planning and Scheduling, [S. l.], v. 35, n. 1, p. 2-10, 2025. DOI: 10.1609/icaps.v35i1.36095. Disponível em: https://ojs.aaai.org/index.php/ICAPS/article/view/36095. Acesso em: 25 apr. 2026.