An Empirical Evaluation of Genetic Algorithms on Noisy Objective Functions

Genetic algorithms have particular potential as a tool for optimization when the evaluation function is noisy. Several types of genetic algorithm are compared against a mutation driven stochastic hill-climbing algorithm on a standard set of benchmark functions which have had Gaussian noise added to them. Diierent criteria for judging the eeectiveness of the search are also considered. The genetic algorithms used in these comparisons include an elitist simple genetic algorithm, the CHC adaptive search algorithm and the delta coding genetic algorithm. Finally several hybrid genetic algorithms are described and compared on a very large and noisy seismic data imaging problem.