Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1366655,
author = {Brázdil, Tomáš and Bartocci, Ezio and Milios, Dimitrios and Sanguinetti, Guido and Bortolussi, Luca},
address = {Quebec City},
booktitle = {Proceedings of QEST 2016},
doi = {http://dx.doi.org/10.1007/978-3-319-43425-4_17},
keywords = {continuous-time Markov decision processes; reachability; gradient descent},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Quebec City},
isbn = {978-3-319-43424-7},
pages = {244-259},
publisher = {Springer},
title = {Policy Learning for Time-Bounded Reachability in Continuous-Time Markov Decision Processes via Doubly-Stochastic Gradient Ascent},
year = {2016}
}
TY - JOUR
ID - 1366655
AU - Brázdil, Tomáš - Bartocci, Ezio - Milios, Dimitrios - Sanguinetti, Guido - Bortolussi, Luca
PY - 2016
TI - Policy Learning for Time-Bounded Reachability in Continuous-Time Markov Decision Processes via Doubly-Stochastic Gradient Ascent
PB - Springer
CY - Quebec City
SN - 9783319434247
KW - continuous-time Markov decision processes
KW - reachability
KW - gradient descent
N2 - Continuous-time Markov decision processes are an important class of models in a wide range of applications, ranging from cyber-physical systems to synthetic biology. A central problem is how to devise a policy to control the system in order to maximise the probability of satisfying a set of temporal logic specifications. Here we present a novel approach based on statistical model checking and an unbiased estimation of a functional gradient in the space of possible policies. The statistical approach has several advantages over conventional approaches based on uniformisation, as it can also be applied when the model is replaced by a black box, and does not suffer from state-space explosion. The use of a stochastic gradient to guide our search considerably improves the efficiency of learning policies. We demonstrate the method on a proof-of-principle non-linear population model, showing strong performance in a non-trivial task.
ER -
BRÁZDIL, Tomáš, Ezio BARTOCCI, Dimitrios MILIOS, Guido SANGUINETTI and Luca BORTOLUSSI. Policy Learning for Time-Bounded Reachability in Continuous-Time Markov Decision Processes via Doubly-Stochastic Gradient Ascent. In \textit{Proceedings of QEST 2016}. Quebec City: Springer, 2016, p.~244-259. ISBN~978-3-319-43424-7. Available from: https://dx.doi.org/10.1007/978-3-319-43425-4\_{}17.
|
