Package org.moeaframework.core.operator

Class AdaptiveMultimethodVariation

java.lang.Object
org.moeaframework.core.operator.AbstractCompoundVariation<Variation>
org.moeaframework.core.operator.AdaptiveMultimethodVariation
All Implemented Interfaces:
Configurable, Variation
public class AdaptiveMultimethodVariation extends AbstractCompoundVariation<Variation>
Auto-adaptive multi-method recombination operator. Applies operators with probabilities proportional to the number of offspring produced by each operator in the archive.

  • Constructor Details

    • AdaptiveMultimethodVariation

      public AdaptiveMultimethodVariation(Population archive)
      Constructs an auto-adaptive multi-method recombination operator with the specified archive for updating probabilities.
      Parameters:
      archive - the archive used to update the probabilities

  • Method Details

    • getName

      public String getName()
      Description copied from class: AbstractCompoundVariation
      Returns the name of this variation operator. If no name has been assigned through AbstractCompoundVariation.setName(String), a name is generated which identifies the underlying operators.
      Specified by:
      getName in interface Variation
      Overrides:
      getName in class AbstractCompoundVariation<Variation>
      Returns:
      the name of this variation operator

    • getUpdateWindow

      public int getUpdateWindow()
      Returns the number of invocations of the evolve method between updating the operator selection probabilities.
      Returns:
      the number of invocations of the evolve method between updating the operator selection probabilities

    • addOperator

      public void addOperator(Variation operator)
      Adds an operator to be used in the auto-adaptive multi-method recombination.
      Parameters:
      operator - the operator

    • getNumberOfOperators

      public int getNumberOfOperators()
      Returns the number of available operators.
      Returns:
      the number of available operators

    • getOperator

      public Variation getOperator(int index)
      Returns the operator at the specified index.
      Parameters:
      index - the index of the operator to be returned
      Returns:
      the operator at the specified index

    • getOperatorProbability

      public double getOperatorProbability(int index)
      Returns the probability that the operator at the specified index is applied.
      Parameters:
      index - the index of the operator whose probability is returned
      Returns:
      the probability that the operator at the specified index is applied

    • getOperatorProbabilities

      protected double[] getOperatorProbabilities()
      Returns the array of probabilities of applying each operator.
      Returns:
      the array of probabilities of applying each operator

    • selectOperator

      protected int selectOperator()
      Returns the index of one of the available operators randomly selected using the probabilities.
      Returns:
      the index of one of the available operators randomly selected using the probabilities

    • evolve

      public Solution[] evolve(Solution[] parents)
      Description copied from interface: Variation
      Evolves one or more parent solutions (specified by getArity) and produces one or more child solutions. By contract, the parents must not be modified. The copy constructor should be used to create copies of the parents with these copies subsequently modified.
      Specified by:
      evolve in interface Variation
      Overrides:
      evolve in class AbstractCompoundVariation<Variation>
      Parameters:
      parents - the array of parent solutions
      Returns:
      an array of child solutions

    • getArity

      public int getArity()
      Description copied from interface: Variation
      Returns the number of solutions that must be supplied to the evolve method.
      Specified by:
      getArity in interface Variation
      Overrides:
      getArity in class AbstractCompoundVariation<Variation>
      Returns:
      the number of solutions that must be supplied to the evolve method