Paper Info
Title
Policy learning in continuous-time Markov decision processes using Gaussian Processes.
Abstract
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-priori 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.
Year
DOI
Venue
2017
10.1016/j.peva.2017.08.007
Performance Evaluation
Keywords
Field
DocType
Continuous-Time Markov decision processes,Gaussian processes,Machine learning,Policy learning
Convergence (routing),Discretization,Gradient descent,Modeling and simulation,Computer science,Markov decision process,Theoretical computer science,Gaussian process,Temporal logic,Queue management system
Journal
Volume
Issue
ISSN
116
C
0166-5316
Citations 
PageRank 
References 
1
0.35
28
Authors
5
Name
Order
Citations
PageRank
Ezio Bartocci173357.55
Luca Bortolussi266358.88
Tomás Brázdil316116.23
Dimitrios Milios4595.84
Guido Sanguinetti577257.09