A Robust and Efficient Evolutionary Algorithm based on Probabilistic Model

Evolutionary algorithms commonly search for the best solutions by maintaining a population of individuals that evolves from one generation to the next. The evolution consists of selecting a set of individuals from the population and applying, to some subsets of it, recombination operators that create new solutions. In this paper, Estimation of distribution algorithms arise as an alternative to genetic algorithms. Instead of exchanging information between individuals through genetic operators, Estimation of distribution algorithms use machine learning methods to extract relevant features of the search space through the selected individuals of the population. The replacement of crossover and mutation operators by probabilistic models can bring some benefits. The most important benefit could be that the structural component of the probabilistic model can provide explicit information about the interactions among the variables used to codify the problem solutions.