Benefits of a Periodic Selection Event in Evolutionary Strategy Algorithms

We compare common, fixed population size evolutionary strategies with a strategy incorporating a growing population size and intermittent selection events. In the latter strategy, the population size grows geometrically and selection free every generation. After a fixed number of generations, a selection event occurs which kills many of the individuals in the population and reduces the population size back to an initial value. The quality of solutions and speed of this algorithm are compared using four real-valued problem domains, to common evolutionary strategy algorithms based on (mu, lambda) and (mu+lambda), with promising results.