Policy learning for time-bounded reachability in continuous-time Markov decision processes via doubly-stochastic gradient ascent

DOI10.1007/978-3-319-43425-4_17zbMath1380.65024arXiv1605.09703OpenAlexW2417191198MaRDI QIDQ1693106

Luca Bortolussi, Guido Sanguinetti, Ezio Bartocci, Dimitrios Milios, Tomáš Brázdil

Publication date: 11 January 2018

Full work available at URL: https://arxiv.org/abs/1605.09703

zbMATH Keywords

unbiased estimationcontinuous-time Markov decision processesstatistical model checkingnonlinear population model

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05) Population dynamics (general) (92D25)

Related Items (2)

ARES: Adaptive Receding-Horizon Synthesis of Optimal Plans ⋮ ARMed SPHINCS

This page was built for publication: Policy learning for time-bounded reachability in continuous-time Markov decision processes via doubly-stochastic gradient ascent