Ovidiu Gheorghies, Henri Luchian, Adriana Gheorghies

The aim of this paper is to show that exploiting knowledge extracted from the optimization process is important for the success of an evolutionary solver. In the context of NK fitness landscapes, we identify two causes for the difficulty of an optimization problem: the intrinsic combinatorial difficulty and the random-search hybridization.

We apply these concepts for the royal road fitness landscape. Experimental results indicate that Integrated-Adaptive Genetic Algorithms (IAGA) are particularly suited for tackling random search hybridization.

A learn-as-you-go system aimed at a fine-grained adaptation of operators behavior increases the solving power and convergence speed of IAGA. We conclude that the royal road problem is actually being “royal” for the traditional GA, but for a class of adaptive genetic algorithms.

Full Document (PDF)

Bibtex

@TechReport{wrriaga,
    author = "Ovidiu Gheorghie{c s} and Henri Luchian and Adriana Gheorghie{c s}",
    title = "Walking the Royal Road with Integrated-Adaptive Genetic Algorithms",
    institution = "``Al.I.Cuza'' University of Ia{c s}i, Faculty of Computer Science",
    year = "2005",
    number = "TR 05-04",
    url = "https://publications.info.uaic.ro/technical-reports/archive/tr05-04-2005-walking-the-royal-road-with-integrated-adaptive-genetic-algorithms/"
}