In this section
@article{Liu:2026:10.1287/opre.2024.0934,
author = {Liu, H and Wiesemann, W and Yue, M-C},
doi = {10.1287/opre.2024.0934},
journal = {Operations Research},
title = {An MILP-based solution scheme for factored Markov decision processes},
url = {http://dx.doi.org/10.1287/opre.2024.0934},
year = {2026}
}
TY - JOUR
AB - Factored Markov decision processes (MDPs) are a prominent paradigm within the artificial intelligence community for modeling and solving large-scale MDPs whose rewards and dynamics decompose into smaller, loosely interacting components. Through the use of value function approximations, dynamic Bayesian networks and context-specific independence, factored MDPs can achieve an exponential reduction in the state space of an MDP and thus scale to problem sizes that are beyond the reach of classical MDP algorithms. However, factored MDPs are typically solved using custom-designed algorithms that can require meticulous implementationsand considerable fine-tuning. In this paper, we propose a mathematical programming approach to solving factored MDPs. Unlike existing solution schemes, our approach leverages off-the-shelf solvers, which enables streamlined implementation and maintenance. Moreover, we exploit the factored structure in both state and action spaces, and we employ feature representations to unify existing methods while taking advantage of context-specific independence in problem classes that other approaches cannot solve efficiently. To further enhance scalability, we introduce a feature learning scheme that automatically identifies informative features and a dynamic basisapproximation scheme that adaptively refines our value function approximations. Our numerical experiments demonstrate the potential of our approach.
AU - Liu,H
AU - Wiesemann,W
AU - Yue,M-C
DO - 10.1287/opre.2024.0934
PY - 2026///
SN - 0030-364X
TI - An MILP-based solution scheme for factored Markov decision processes
T2 - Operations Research
UR - http://dx.doi.org/10.1287/opre.2024.0934
ER -