Prestwich S.D.Tarim S.A.Rossi R.Hnich B.2023-06-162023-06-162009364204427197836420442740302-9743https://doi.org/10.1007/978-3-642-04428-1_35https://hdl.handle.net/20.500.14365/3401DIMACS;DAUPHINE UNIVERSITE PARIS;CNRS;COST;EUROPEAN SCIENCE FOUNDATION1st International Conference on Algorithmic Decision Theory, ADT 2009 -- 20 October 2009 through 23 October 2009 -- Venice -- 77991Stochastic inventory control in multi-echelon systems poses hard problems in optimisation under uncertainty. Stochastic programming can solve small instances optimally, and approximately solve large instances via scenario reduction techniques, but it cannot handle arbitrary nonlinear constraints or other non-standard features. Simulation optimisation is an alternative approach that has recently been applied to such problems, using policies that require only a few decision variables to be determined. However, to find optimal or near-optimal solutions we must consider exponentially large scenario trees with a corresponding number of decision variables. We propose a neuroevolutionary approach: using an artificial neural network to approximate the scenario tree, and training the network by a simulation-based evolutionary algorithm. We show experimentally that this method can quickly find good plans. © 2009 Springer-Verlag Berlin Heidelberg.eninfo:eu-repo/semantics/openAccessAlternative approachArtificial Neural NetworkDecision variablesHard problemsMultiechelonNear-optimal solutionsNon-linear constraintsOptimisationsReduction techniquesScenario treeSimulation optimisationSimulation-basedStochastic inventoryComputer simulationDecision treesEvolutionary algorithmsGame theoryInventory controlOptimizationStochastic systemsNeural networksConference Object10.1007/978-3-642-04428-1_352-s2.0-71549146592