Abstract: |
We describe a set of measures to examine the behavior of the GeneticAlgorithm (GA) in dynamic environments. We describe how to use bothaverage and best measures to look at performance, satisficability,robustness, and diversity. We use these measures to examine GAbehavior with a recently devised dynamic test suite, the Shaky LadderHyperplane-Defined Functions (sl-hdf's). This test suite can generaterandom problems with similar levels of difficulty and provides aplatform allowing systematic controlled observations of the GA indynamic environments. e examine the results of these measures in twodifferent versions of the sl-hdf's, one static and oneregularly-changing. e provide explanations for the observations inthese two different environments, and give suggestions as to futurework. |
