Playing Against a Stationary Opponent
Mathematics of Operations Research · 13.07.2026
DOI: 10.1287/moor.2025.0904 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics of Operations Research, online erschienen am 13.07.2026. Verfasst von Julien Grand-Clément und 1 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben.
Abstract (Originalsprache)
This paper investigates properties of Blackwell [Formula: see text]-optimal strategies in zero-sum stochastic games when the adversary is restricted to stationary strategies, motivated by applications to robust Markov decision processes. For a class of absorbing games (including generalized Big Match games), we show that Markovian Blackwell [Formula: see text]-optimal strategies may fail to exist, yet we prove the existence of Blackwell [Formula: see text]-optimal strategies that can be implemented by a two-state automaton whose internal transitions are independent of actions. For more general absorbing games, however, there need not exist Blackwell [Formula: see text]-optimal strategies that are independent of the adversary’s decisions. Our findings provide new insights into the properties of optimal policies for robust Markov decision processes.
Zitieren
APA
Grand-Clément, J., & Vieille, N. (2026). Playing Against a Stationary Opponent. Mathematics of Operations Research. https://doi.org/10.1287/moor.2025.0904
Vancouver
Grand-Clément J, Vieille N. Playing Against a Stationary Opponent. Mathematics of Operations Research. 2026. doi:10.1287/moor.2025.0904
BibTeX
@article{GrandClment2026,
author = {Grand-Clément, Julien and Vieille, Nicolas},
title = {Playing Against a Stationary Opponent},
journal = {Mathematics of Operations Research},
year = {2026},
doi = {10.1287/moor.2025.0904}
}
EUVIMED