Learning Algorithms for Verification of Markov Decision Processes

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F25%3A00142495" target="_blank" >RIV/00216224:14330/25:00142495 - isvavai.cz</a>

Result on the web

<a href="https://theoretics.episciences.org/14694" target="_blank" >https://theoretics.episciences.org/14694</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.46298/theoretics.25.10" target="_blank" >10.46298/theoretics.25.10</a>

Result language

angličtina

Original language name

Learning Algorithms for Verification of Markov Decision Processes

Original language description

We present a general framework for applying learning algorithms and heuristical guidance to the verification of Markov decision processes (MDPs). The primary goal of our techniques is to improve performance by avoiding an exhaustive exploration of the state space, instead focussing on particularly relevant areas of the system, guided by heuristics. Our work builds on the previous results of Br{á}zdil et al., significantly extending it as well as refining several details and fixing errors. The presented framework focuses on probabilistic reachability, which is a core problem in verification, and is instantiated in two distinct scenarios. The first assumes that full knowledge of the MDP is available, in particular precise transition probabilities. It performs a heuristic-driven partial exploration of the model, yielding precise lower and upper bounds on the required probability. The second tackles the case where we may only sample the MDP without knowing the exact transition dynamics. Here, we obtain probabilistic guarantees, again in terms of both the lower and upper bounds, which provides efficient stopping criteria for the approximation. In particular, the latter is an extension of statistical model-checking (SMC) for unbounded properties in MDPs. In contrast to other related approaches, we do not restrict our attention to time-bounded (finite-horizon) or discounted properties, nor assume any particular structural properties of the MDP.

Czech name

—

Czech description

—

Type

J_SC - Article in a specialist periodical, which is included in the SCOPUS database

CEP classification

—

OECD FORD branch

10200 - Computer and information sciences

Project

—

Continuities

V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

TheoretiCS

ISSN

2751-4838

e-ISSN

2751-4838

Volume of the periodical

4

Issue of the periodical within the volume

13268

Country of publishing house

DE - GERMANY

Number of pages

82

Pages from-to

1-82

UT code for WoS article

—

EID of the result in the Scopus database

2-s2.0-105031089413