English

Reoptimization Nearly Solves Weakly Coupled Markov Decision Processes

Optimization and Control 2024-05-08 v2 Probability

Abstract

We propose a new policy, called the LP-update policy, to solve finite horizon weakly-coupled Markov decision processes. The latter can be seen as multi-constraint multi-action bandits, and generalize the classical restless bandit problems. Our solution is based on re-solving periodically a relaxed version of the original problem, that can be cast as a linear program (LP). When the problem is made of NN statistically identical sub-components, we show that the LP-update policy becomes asymptotically optimal at rate O(T2/N)O(T^2/\sqrt{N}). This rate can be improved to O(T/N)O(T/\sqrt{N}) if the problem satisfies some ergodicity property and to O(1/N)O(1/N) if the problem is non-degenerate. The definition of non-degeneracy extends the same notion for restless bandits. By using this property, we also improve the computational efficiency of the LP-update policy. We illustrate the performance of our policy on randomly generated examples, as well as a generalized applicant screening problem, and show that it outperforms existing heuristics.

Keywords

Cite

@article{arxiv.2211.01961,
  title  = {Reoptimization Nearly Solves Weakly Coupled Markov Decision Processes},
  author = {Nicolas Gast and Bruno Gaujal and Chen Yan},
  journal= {arXiv preprint arXiv:2211.01961},
  year   = {2024}
}

Comments

29 pages. Preprint

R2 v1 2026-06-28T05:07:34.391Z