ABSTRACT
Evolutionary algorithms are a special family of optimization algorithms. Instead of striving to improve a single trial solution, like the techniques presented in Chapter 6, they maintain a population of candidate solutions. The population as whole evolves toward the optimum, although the population may contain many poor solutions, especially during the early stages of evolution. In common with simulated annealing, evolutionary algorithms are generally designed to start with an exploration phase. During this phase, the population roams the search space seeking good quality regions. As there is a population of candidate solutions, several regions can be explored at the same time. As evolution progresses, the algorithm migrates from exploration to exploitation, that is, seeking the peak ¡tness of the region that is assumed, by this stage, to contain the global optimum.
