Saved in:
Bibliographic Details
Main Authors: Mukherjee, Dibyangshu, Kalyanakrishnan, Shivaram
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.00795
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909598686904320
author Mukherjee, Dibyangshu
Kalyanakrishnan, Shivaram
author_facet Mukherjee, Dibyangshu
Kalyanakrishnan, Shivaram
contents Howard's Policy Iteration (HPI) is a classic algorithm for solving Markov Decision Problems (MDPs). HPI uses a "greedy" switching rule to update from any non-optimal policy to a dominating one, iterating until an optimal policy is found. Despite its introduction over 60 years ago, the best-known upper bounds on HPI's running time remain exponential in the number of states -- indeed even on the restricted class of MDPs with only deterministic transitions (DMDPs). Meanwhile, the tightest lower bound for HPI for MDPs with a constant number of actions per state is only linear. In this paper, we report a significant improvement: a subexponential upper bound for HPI on DMDPs, which is parameterised by the bit-size of the rewards, while independent of the discount factor. The same upper bound also applies to DMDPs with only two possible rewards (which may be of arbitrary size).
format Preprint
id arxiv_https___arxiv_org_abs_2505_00795
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Howard's Policy Iteration is Subexponential for Deterministic Markov Decision Problems with Rewards of Fixed Bit-size and Arbitrary Discount Factor
Mukherjee, Dibyangshu
Kalyanakrishnan, Shivaram
Artificial Intelligence
Howard's Policy Iteration (HPI) is a classic algorithm for solving Markov Decision Problems (MDPs). HPI uses a "greedy" switching rule to update from any non-optimal policy to a dominating one, iterating until an optimal policy is found. Despite its introduction over 60 years ago, the best-known upper bounds on HPI's running time remain exponential in the number of states -- indeed even on the restricted class of MDPs with only deterministic transitions (DMDPs). Meanwhile, the tightest lower bound for HPI for MDPs with a constant number of actions per state is only linear. In this paper, we report a significant improvement: a subexponential upper bound for HPI on DMDPs, which is parameterised by the bit-size of the rewards, while independent of the discount factor. The same upper bound also applies to DMDPs with only two possible rewards (which may be of arbitrary size).
title Howard's Policy Iteration is Subexponential for Deterministic Markov Decision Problems with Rewards of Fixed Bit-size and Arbitrary Discount Factor
topic Artificial Intelligence
url https://arxiv.org/abs/2505.00795