Semismooth newton methods for risk-averse Markov decision processes
Automatica · 2026-06 · 188 · 112889
DOI: 10.1016/j.automatica.2026.112889 ↗Kurz gefasst
Fachartikel in der Zeitschrift Automatica, 2026-06. Verfasst von Matilde Gargiani und 3 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Horizon 2020, European Research Council.
Abstract (Originalsprache)
Inspired by semismooth Newton methods, we propose a general framework for designing solution methods with convergence guarantees for risk-averse Markov decision processes. Our approach accommodates a wide variety of risk measures by leveraging the assumption of Markovian coherent risk measures. To demonstrate the versatility and effectiveness of this framework, we design three distinct solution methods, each with proven convergence guarantees and competitive empirical performance. Validation results on benchmark problems demonstrate the competitive performance of our methods. Furthermore, we establish that risk-averse policy iteration can be interpreted as an instance of semismooth Newton's method. This insight explains its superior convergence properties compared to risk-averse value iteration. The core contribution of our work, however, lies in developing an algorithmic framework inspired by semismooth Newton methods, rather than evaluating specific risk measures or advocating for risk-averse approaches over risk-neutral ones in particular applications.
Förderung
- Horizon 2020
- European Research Council
Zitieren
APA
Gargiani, M., Micheli, F., Tsiamis, A., & Lygeros, J. (2026). Semismooth newton methods for risk-averse Markov decision processes. Automatica, 188, 112889. https://doi.org/10.1016/j.automatica.2026.112889
Vancouver
Gargiani M, Micheli F, Tsiamis A, Lygeros J. Semismooth newton methods for risk-averse Markov decision processes. Automatica. 2026;188:112889. doi:10.1016/j.automatica.2026.112889
BibTeX
@article{Gargiani2026,
author = {Gargiani, Matilde and Micheli, Francesco and Tsiamis, Anastasios and Lygeros, John},
title = {Semismooth newton methods for risk-averse Markov decision processes},
journal = {Automatica},
year = {2026},
volume = {188},
pages = {112889},
doi = {10.1016/j.automatica.2026.112889}
}
EUVIMED