Yet another distributional Bellman equation
European Journal of Operational Research · 2026-10 · 334 (2) · 392-403
DOI: 10.1016/j.ejor.2026.03.010 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Operational Research, 2026-10. Verfasst von Nicole Bäuerle und 2 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We consider non-standard Markov Decision Processes (MDPs) where the target function is not only a simple expectation of the accumulated reward. Instead, we consider rather general functionals of the joint distribution of terminal state and accumulated reward which have to be optimized. For finite state and compact action space, we show how to solve these problems by defining a lifted MDP whose state space is the space of distributions over the true states of the process. We derive a Bellman equation in this setting, which can be considered as a distributional Bellman equation. Well-known cases like the standard MDP and quantile MDPs are shown to be special examples of our framework. We also apply our model to a variant of an optimal transport problem.
Zitieren
APA
Bäuerle, N., Göll, T., & Jaśkiewicz, A. (2026). Yet another distributional Bellman equation. European Journal of Operational Research, 334(2), 392-403. https://doi.org/10.1016/j.ejor.2026.03.010
Vancouver
Bäuerle N, Göll T, Jaśkiewicz A. Yet another distributional Bellman equation. European Journal of Operational Research. 2026;334(2):392-403. doi:10.1016/j.ejor.2026.03.010
BibTeX
@article{Buerle2026,
author = {Bäuerle, Nicole and Göll, Tamara and Jaśkiewicz, Anna},
title = {Yet another distributional Bellman equation},
journal = {European Journal of Operational Research},
year = {2026},
volume = {334},
number = {2},
pages = {392--403},
doi = {10.1016/j.ejor.2026.03.010}
}
EUVIMED