Designing asymptotically optimal policies for continuous-time weakly coupled MDPs
ACM SIGMETRICS Performance Evaluation Review · 31.03.2026 · 53 (4) · 24-25
DOI: 10.1145/3797823.3797834 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM SIGMETRICS Performance Evaluation Review, online erschienen am 31.03.2026. Verfasst von M. Perbal und 2 weiteren Autor:innen. Die Arbeit nennt 8 Literaturangaben.
Abstract (Originalsprache)
We study the continuous-time Weakly Coupled Markov Decision Process (WCMDP), a class of decision problems involving multiple interacting Markov processes (or ''arms'') subject to shared resource constraints. We present a general framework for policy design using a combination of an underlying Markov process and a sequence of mappings. Our main theoretical result establishes suffifient conditions for asymptotic optimality as the number of arms grows. We construct both deterministic and randomized policies based on a solution to a linear program (LP). These policies initially assign actions to arms—either proportionally (deterministic) or randomly—based on conditional measures derived from the LP. As this initial allocation may violate feasibility constraints, we introduce a mapping to enforce the resource constraints are satisfied.
Zitieren
APA
Perbal, M., Prabhu, B., & Verloop, I. (2026). Designing asymptotically optimal policies for continuous-time weakly coupled MDPs. ACM SIGMETRICS Performance Evaluation Review, 53(4), 24-25. https://doi.org/10.1145/3797823.3797834
Vancouver
Perbal M, Prabhu B, Verloop I. Designing asymptotically optimal policies for continuous-time weakly coupled MDPs. ACM SIGMETRICS Performance Evaluation Review. 2026;53(4):24-25. doi:10.1145/3797823.3797834
BibTeX
@article{Perbal2026,
author = {Perbal, M. and Prabhu, B.J. and Verloop, I.M.},
title = {Designing asymptotically optimal policies for continuous-time weakly coupled MDPs},
journal = {ACM SIGMETRICS Performance Evaluation Review},
year = {2026},
volume = {53},
number = {4},
pages = {24--25},
doi = {10.1145/3797823.3797834}
}
EUVIMED