Verification of general Markov decision processes by approximate similarity relations and policy refinement

S. Haesaert, S. Esmaeil, S. Soudjani, A. Abate

Research output: Contribution to journalArticleAcademic

6 Citations (Scopus)
50 Downloads (Pure)

Abstract

In this work we introduce new approximate similarity relations that are shown to be key for policy (or control) synthesis over general Markov decision processes. The models of interest are discrete-time Markov decision processes, endowed with uncountably-infinite state spaces and metric output (or observation) spaces. The new relations, underpinned by the use of metrics, allow in particular for a useful trade-off between deviations over probability distributions on states, and distances between model outputs. We show that the new probabilistic similarity relations, inspired by a notion of simulation developed for finite-state models, can be effectively employed over general Markov decision processes for verification purposes, and specifically for control refinement from abstract models.
Original languageEnglish
Article number1605.09557v1
Pages (from-to)1-36
JournalarXiv.org, e-Print Archive, Physics
Publication statusPublished - 31 May 2016

Fingerprint Dive into the research topics of 'Verification of general Markov decision processes by approximate similarity relations and policy refinement'. Together they form a unique fingerprint.

Cite this