Self-adaptation using Multi-chromosomes

Self-adaptation is one of the most promising areas of research in evolutionary computation as it adapts the algorithm to the problem while solving the problem. In this paper we extend self-adaptation to nonnumeric problems in Genetic Algorithms by using a multi-chromosome representation. We modify a genetic algorithm for a Cutting Stock Problem to self-adapt two strategy parameters; the results indicate that the approach works quite well. I. Introduction Self-adaptation is an important area of research in Evolutionary Computation as we use it to adapt an evolutionary algorithm to the problem as it is solving the problem. Self-adaptation, where the strategy parameters being self-adapted form part of the representation of the individual, and undergo mutation and/or recombination has been used in Evolution Strategies (Schwefel, 1995), Evolutionary Programming (Saravanan & Fogel, 1994) and Genetic Algorithms (Back, 1992; Hinterding, 1995). Selfadaptation has been to optimise of mainly num..