Policy learning in Continuous-Time Markov Decision Processes using Gaussian Processes

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

Research output: Contribution to journalArticlepeer-review


Continuous-time Markov decision processes provide a very powerful mathematical framework to solve policy-making problems in a wide range of applications, ranging from the control of populations to cyber-physical systems. The key problem to solve for these models is to efficiently compute an optimal policy to control the system in order to maximise the probability of satisfying a set of temporal logic specifications. Here we introduce a novel method based on
statistical model checking and an unbiased estimation of a functional gradient
in the space of possible policies. Our approach presents several advantages over
the classical methods based on discretisation techniques, as it does not assume
the a-priority knowledge of a model that can be replaced by a black-box, and does not suffer from state-space explosion. The use of a stochastic moment-based gradient ascent algorithm to guide our search considerably improves the efficiency of learning policies and accelerates the convergence using the momentum term. We demonstrate the strong performance of our approach on two examples of non-linear population models: an epidemiology model with no permanent recovery and a queuing system with non-deterministic choice.
Original languageEnglish
Pages (from-to)84-100
Number of pages28
JournalPerformance Evaluation
Early online date2 Sep 2017
Publication statusPublished - 1 Nov 2017


Dive into the research topics of 'Policy learning in Continuous-Time Markov Decision Processes using Gaussian Processes'. Together they form a unique fingerprint.

Cite this