Prestwich S.D.Tarim S.A.Rossi R.Hnich B.2023-06-162023-06-162010364213519697836421351940302-9743https://doi.org/10.1007/978-3-642-13520-0_30https://hdl.handle.net/20.500.14365/3404The ARTIST Design;Network of Excellence;The Institute for Computational Sustainability (ICS);The Cork Constraint Computation Center;The Association for Constraint Programming (ACP)7th International Conference on Integration of AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems, CPAIOR 2010 -- 14 June 2010 through 18 June 2010 -- Bologna -- 81368Stochastic Constraint Programming is an extension of Constraint Programming for modelling and solving combinatorial problems involving uncertainty. A solution to such a problem is a policy tree that specifies decision variable assignments in each scenario. Several complete solution methods have been proposed, but the authors recently showed that an incomplete approach based on neuroevolution is more scalable. In this paper we hybridise neuroevolution with constraint filtering on hard constraints, and show both theoretically and empirically that the hybrid can learn more complex policies more quickly. © 2010 Springer-Verlag.eninfo:eu-repo/semantics/openAccessCombinatorial problemComplete solutionsConstraint programmingDecision variablesHard constraintsNeuroevolutionStochastic constraintsCombinatorial optimizationComputer programmingConstraint theoryDecision makingStochastic systemsProblem solvingConference Object10.1007/978-3-642-13520-0_302-s2.0-77955452287