📖
Anytime-Valid Monitoring of Robust Stochastic Models
Martin Kurečka, Roman Andriushchenko, Milan Češka, Nicola Paoletti, Petr Novotný

Anytime-Valid Monitoring of Robust Stochastic Models

Science & Mathematics Published 2026 Verification Pending

Overview & Synopsis

Formal methods provide a principal approach to obtaining safety guarantees for autonomous agents. Their key bottleneck is their reliance on a formal model (e.g., a Markov decision process) describing the agent-environment interaction. Learning or crafting the model is an error-prone process, which undermines the guarantees offered by formal methods. Robust models account for modelling uncertainty, but may still fail to capture the true environment. This issue can be addressed through \emph{runtime model monitoring}, which aims to raise an alarm when a likely model-environment discrepancy is detected, while keeping the probability of false alarm bounded. Existing approaches impose various assumptions and do not clearly explain the rationale behind their design choices, leaving the broader design space for these monitors somewhat opaque. In this paper, we formalise the design space of monitors for robust stochastic models through the lens of \emph{parameterised sequential betting} algorithms, highlighting the importance of \emph{observation feature} design (choosing what information about the history the monitor uses) and \emph{bet design} (how rich a family of betting rules the monitor can represent). We show that our framework generalizes the existing approaches, and we use its formalization to propose a new \emph{mixture of linear monitors (ML)} design. We prove that these ML monitors achieve an asymptotically optimal detection time within the class of linear monitors, making them a principled choice for our monitoring problem. Our experiments confirm that ML monitors significantly reduce detection times compared to existing monitors and can effectively exploit more complex observation features.

Indexed from repository: arXiv (arxiv.org)
Loading document from verified source...
Keyboard Shortcuts: ← / → for pages • + / - for zoom • 0 to fit width Powered by Mozilla PDF.js v3.11

Document Information

Document Title Anytime-Valid Monitoring of Robust Stochastic Models
Author / Organization Martin Kurečka, Roman Andriushchenko, Milan Češka, Nicola Paoletti, Petr Novotný
Subject & Discipline cs.LO
Categories Science & Mathematics
Publication Year 2026
License / Rights arXiv Open Access / Creative Commons
Resource Verification Listed PDF (Verification Pending)
Original Host Website arXiv (arxiv.org)
File Format application/pdf (Portable Document Format)
Language EN
Catalog ID DOC-273221
Original Source Link Visit Source Page on arxiv.org »