Mukherjee, Dibyangshu, and Shivaram Kalyanakrishnan. “Howard’s Policy Iteration Is Subexponential for Deterministic Markov Decision Problems With Rewards of Fixed Bit-Size and Arbitrary Discount Factor”. Proceedings of the International Conference on Automated Planning and Scheduling 35, no. 1 (September 16, 2025): 84-92. Accessed May 4, 2026. https://ojs.aaai.org/index.php/ICAPS/article/view/36104.