An algorithm called SAMOPT is developed for optimizing the response function of simulation models that describe systems exhibiting stochastic behavior. Because of the stochastic nature of these simulated systems, the result of each evaluation of response by simulation is only a noisy (i.e., uncertain) observation of the true response. The SAMOPT algorithm uses these noisy responses to find a set of values for decision variables of the system such that the true response is optimized. Principles of the Stochastic Approximation Method have been used in developing this algorithm. The SAMOPT algorithm also allows for the case where the decision variables are subject to a set of linear constraints. Comparison of results between applications of SAMOPT and another well-known method are given for problems and a simulation model.
