Agarwal, Pratyush, Mulinti Shaik Wajid, and Shivaram Kalyanakrishnan. “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 35, no. 1 (September 16, 2025): 2-10. Accessed May 4, 2026. https://ojs.aaai.org/index.php/ICAPS/article/view/36095.