ABSTRACT
This chapter aims to give a summary of evolutionary computation (EC) techniques. The summary includes a general description of the main families of algorithms belonging to the EC field as well as their main components. Also, describe their evolution through the last years including advances in constraint handling methods, parallel models and algorithms, methods for dynamic environments, and multiobjective optimization, and so on. At the start of an Evolutionary Algorithms (EAs), an initial population of individuals is generated by applying a function ι to the genotype space G. Function ι might represent a random procedure that generates individuals at random, or it might represent a heuristic seeding procedure. Every possible instantiation of this general framework gives rise to different EAs. In fact, it is possible to distinguish among different EA families by considering some guidelines on how to perform this instantiation. Most commonly used in EAs is the representation of solutions as bit-strings or as permutations of n integer number.
