ec.multiobjective.nsga2

Class NSGA2Evaluator

java.lang.Object

ec.Evaluator

ec.simple.SimpleEvaluator

ec.multiobjective.nsga2.NSGA2Evaluator

All Implemented Interfaces:

Setup, Singleton, Serializable

public class NSGA2Evaluator
extends SimpleEvaluator

The NSGA2Evaluator is a simple generational evaluator which evaluates every single member of the population (in a multithreaded fashion). Then it reduces the population size to an archive consisting of the best front ranks. When there isn't enough space to fit another front rank, individuals in that final front rank vie for the remaining slots in the archive based on their sparsity.

The evaluator is also responsible for calculating the rank and sparsity values stored in the NSGA2MultiObjectiveFitness class and used largely for statistical information.

NSGA-II has fixed archive size (the population size), and so ignores the 'elites' declaration. However it will adhere to the 'reevaluate-elites' parameter in SimpleBreeder to determine whether to force fitness reevaluation.

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
int[]	originalPopSize The original population size is stored here so NSGA2 knows how large to create the archive (it's the size of the original population -- keep in mind that NSGA2Breeder had made the population larger to include the children.

Fields inherited from class ec.simple.SimpleEvaluator

C_AUTO, cloneProblem, MERGE_BEST, MERGE_MEAN, MERGE_MEDIAN, mergeForm, numTests, P_CHUNK_SIZE, P_CLONE_PROBLEM, P_MERGE, P_NUM_TESTS, pool, V_AUTO, V_BEST, V_MEAN, V_MEDIAN

Fields inherited from class ec.Evaluator

masterproblem, P_IAMSLAVE, P_MASTERPROBLEM, p_problem, P_PROBLEM

Constructor Summary

Constructors

Constructor and Description
NSGA2Evaluator()

Method Summary

Methods

Modifier and Type	Method and Description
ArrayList	assignFrontRanks(Subpopulation subpop) Divides inds into ranks and assigns each individual's rank to be the rank it was placed into.
void	assignSparsity(Individual[] front) Computes and assigns the sparsity values of a given front.
Individual[]	buildArchive(EvolutionState state, int subpop) Build the auxiliary fitness data and reduce the subpopulation to just the archive, which is returned.
void	evaluatePopulation(EvolutionState state) Evaluates the population, then builds the archive and reduces the population to just the archive.
void	setup(EvolutionState state, Parameter base) Sets up the object by reading it from the parameters stored in state, built off of the parameter base base.

Methods inherited from class ec.simple.SimpleEvaluator

evalPopChunk, runComplete

Methods inherited from class ec.Evaluator

closeContacts, initializeContacts, reinitializeContacts

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

originalPopSize

public int[] originalPopSize

The original population size is stored here so NSGA2 knows how large to create the archive (it's the size of the original population -- keep in mind that NSGA2Breeder had made the population larger to include the children.

Constructor Detail

NSGA2Evaluator

public NSGA2Evaluator()

Method Detail

setup

public void setup(EvolutionState state,
         Parameter base)

Description copied from interface: Setup

Sets up the object by reading it from the parameters stored in state, built off of the parameter base base. If an ancestor implements this method, be sure to call super.setup(state,base); before you do anything else.

Specified by:

setup in interface Setup

Overrides:

setup in class SimpleEvaluator

evaluatePopulation

public void evaluatePopulation(EvolutionState state)

Evaluates the population, then builds the archive and reduces the population to just the archive.

Overrides:

evaluatePopulation in class SimpleEvaluator

buildArchive

public Individual[] buildArchive(EvolutionState state,
                        int subpop)

Build the auxiliary fitness data and reduce the subpopulation to just the archive, which is returned.

assignFrontRanks

public ArrayList assignFrontRanks(Subpopulation subpop)

Divides inds into ranks and assigns each individual's rank to be the rank it was placed into. Each front is an ArrayList.

assignSparsity

public void assignSparsity(Individual[] front)

Computes and assigns the sparsity values of a given front.