edaSelect: Selection Methods

In yasserglez/copulaedas: Estimation of Distribution Algorithms Based on Copulas

Description

Methods for the edaSelect generic function.

Usage

edaSelectTruncation(eda, gen, pop, popEval)
edaSelectTournament(eda, gen, pop, popEval)

Arguments

eda	EDA instance.
gen	Generation.
pop	Matrix with one row for each solution in the population.
popEval	Vector with the evaluation of each solution in pop.

Details

Selection methods determine the solutions to be modeled by the search distribution (selected population). These solutions are usually the most promising solutions of the population. The following selection methods are implemented.

edaSelectTruncation

In truncation selection, the 100 * truncFactor percent of the solutions with the best evaluation in the population are selected. The parameter truncFactor specifies the truncation factor (default value: 0.3). This is the default method of the edaSelect generic function.

edaSelectTournament

In tournament selection, a group of solutions are randomly picked from the population and the best one is selected. This process is repeated as many times as needed to complete the selected population. The parameter tournamentSize specifies the number of solutions randomly picked from the population (default value: 2), selectionSize specifies the size of the selected population (default value: nrow(pop)), and replacement specifies whether to sample with replacement or not (default value: TRUE).

Value

An integer vector with the indexes of the solutions selected from pop.

References

Gonzalez-Fernandez Y, Soto M (2014). copulaedas: An R Package for Estimation of Distribution Algorithms Based on Copulas. Journal of Statistical Software, 58(9), 1-34. http://www.jstatsoft.org/v58/i09/.

Pelikan M (2005). Hierarchical Bayesian Optimization Algorithm. Toward a New Generation of Evolutionary Algorithms. Springer-Verlag.

yasserglez/copulaedas documentation built on June 9, 2021, 10:05 a.m.