Chromosomes and genetic operators for real numbers

In previous chapters, we focused on search problems that inherently deal with the methodic evaluation of states and transitions between states. Consequently, the solutions for these problems were best represented by lists (or arrays) of binary or integer parameters. In contrast to that, this chapter covers problems where the solution space is continuous, meaning the solutions are made up of real (floating-point) numbers. As we mentioned in Chapter 2, Understanding the Key Components of Genetic Algorithms, representing real numbers using binary or integer lists was found to be far from ideal and, instead, lists (or arrays) of real-valued numbers are now considered to be a simpler and better approach.

Reiterating the example from Chapter 2, if we have a problem involving three real-valued parameters, the chromosome will look like the following:

[x 1, x 2, x 3]

Here, x 1, x 2, x 3 represent real...