GA

This optimizer implements the well known standard implementation of Genetic Algorithms. Table 3.7 lists the settings available for this optimizer.

Table 3.7: GA Settings

Name	Description
selection	The type of selection mechanism to use to make new populations. Available are ``Tournament'' and ``RouletteWheel''. Tournament selection is the default
tournament-size	The number of individuals to use for tournament selection. Applies only when selection is ``Tournament''
tournament-probability	Probability with which an individual is selected from a tournament: $p (1 - p)^i$ with $i$ the individual order. You can use a mathematical expression for this setting and use the variable $k$ to indicate the current iteration number. Applies only when selection is ``Tournament''
mutation-probability	The probability with which to mutate an individual. You can use a mathematical expression for this setting and use the variable $k$ to indicate the current iteration number
mutation-rate	The maximum amount of mutation as a fraction of the parameter space. You can use a mathematical expression for this setting and use the variable $k$ to indicate the current iteration number
crossover-probability	The probability with which to use cross-over to create a new individual from two selected parent individuals. You can use a mathematical expression for this setting and use the variable $k$ to indicate the current iteration number

The GA implementation supports both real valued as discrete valued parameters.