Agarwal P, Wajid MS, Kalyanakrishnan S. An Improved Lower Bound on the Length of Locally-Improving Policy Sequences in MDPs with Large Action Sets. ICAPS [Internet]. 2025Sep.16 [cited 2026Apr.29];35(1):2-10. Available from: https://ojs.aaai.org/index.php/ICAPS/article/view/36095