We present fully sequential procedures for steady-state simulation that are designed to select the best of a finite number of simulated systems when "best" is defined by the largest or smallest long-run average performance. We also provide a framework for establishing the asymptotic validity of such procedures and prove the validity of our procedures. An example based on the M/M/1 queue is given. Subject classification: Simulation: ranking and selection; Simulation: steady-state simulation
Seong-Hee Kim, Barry L. Nelson