jcgp.backend.modules.problem

Class Problem

java.lang.Object

jcgp.backend.modules.Module

jcgp.backend.modules.problem.Problem

Direct Known Subclasses:

TestCaseProblem

public abstract class Problem
extends Module

Defines the general behaviour of a CGP problem. The primary function of Problem is to evaluate a population and assign a fitness value to each chromosome.
Problems are free to define whether better fitness means a higher or lower fitness value. In some problem types, it is more convenient to treat fitness 0 as the best possible value. This can be done by changing the fitness orientation to BestFitness.HIGH or BestFitness.LOW as appropriate. Fitness orientation is set to high by default.

When extending this class, the constructor should call a few methods in order to properly construct the problem type: setFunctionSet(), setFileExtension() and setFitnessOrientation(), with the respective arguments. As with all subclasses of Module, setName() and registerParameters() should be used where appropriate as well.

It is advisable to use Resources.reportln() and Resources.report() to print any relevant information. Note that reportln() and report() are affected by the report interval base parameter. Use Resources.println() and Resources.print() to print information regardless of the current generation. See Resources for more information.

Author:

Eduardo Pedroni

See Also:

Module

Constructor Summary

Constructors

Constructor and Description
Problem(Resources resources) Initialises the two problem-wide parameters, maxFitness and bestFitness.

Method Summary

Modifier and Type	Method and Description
abstract void	evaluate(Population population, Resources resources) The most important method of the problem type.
double	getBestFitness()
java.lang.String	getFileExtension()
BestFitness	getFitnessOrientation()
FunctionSet	getFunctionSet()
abstract int	hasImprovement(Population population) Used to assert whether a given population has a chromosome that is an improvement over the current best chromosome.
abstract void	parseProblemData(java.io.File file, ModifiableResources resources) Parses the specified file and uses the parsed data to set up the problem type instance appropriately.
abstract int	perfectSolutionFound(Population population) Used to assert whether a given population contains a perfect solution to the problem.
void	reset() Resets the bestFitness parameter.

Methods inherited from class jcgp.backend.modules.Module

getLocalParameters, toString

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

Problem

public Problem(Resources resources)

Initialises the two problem-wide parameters, maxFitness and bestFitness.

Parameters:

resources - a reference to the experiment's resources.

Method Detail

evaluate

public abstract void evaluate(Population population,
                              Resources resources)

The most important method of the problem type. This is called once per generation, when the new population has been generated.

The basic functionality of this method is to loop through all chromosomes in the population and decode them according to the problem type. The fitness of each chromosome is then calculated using the problem data or otherwise (subjective problem types such as art generation might leave fitness evaluations up to the user) and assigned to the appropriate chromosome.

In addition, realisations of this method should update the value of bestFitness as appropriate, since the value of this parameter is displayed if a GUI is in use.

Parameters:

population - the population to be evaluated.

resources - parameters and utilities for optional reference.

perfectSolutionFound

public abstract int perfectSolutionFound(Population population)

Used to assert whether a given population contains a perfect solution to the problem. It is up to the problem to define what qualifies a perfect solution, as some problems (subject ones such as music and art evolution, for example) might not have perfect solutions at all.

Parameters:

population - the population to search through for a perfect chromosome.

Returns:

the perfect solution index, if one exits, -1 if no perfect solution was found.

hasImprovement

public abstract int hasImprovement(Population population)

Used to assert whether a given population has a chromosome that is an improvement over the current best chromosome. A typical implementation of this method will simply compare chromosome fitness values, though the problem type is free to implement this in any way.

Parameters:

population - the population potentially containing a fitter chromosome.

Returns:

the index of the first chromosome in the population that is an improvement, -1 if none is found.

parseProblemData

public abstract void parseProblemData(java.io.File file,
                                      ModifiableResources resources)

Parses the specified file and uses the parsed data to set up the problem type instance appropriately. Any necessary resource changes can be performed using the provided ModifiableResources instance.

In addition, realisations of this method should update the value of maxFitness where appropriate, as this may be displayed to the user if a GUI is in use.

Parameters:

file - the data file to parse.

resources - a modifiable reference to the experiment's resources.

getFunctionSet

public FunctionSet getFunctionSet()

Returns:

the FunctionSet object used by this problem type.

getFileExtension

public java.lang.String getFileExtension()

Returns:

the file extension accepted by this problem type for problem data files.

getFitnessOrientation

public BestFitness getFitnessOrientation()

Returns:

the fitness orientation of this particular problem.

getBestFitness

public double getBestFitness()

Returns:

the current best fitness, in other words, the fitness value of the fittest chromosome in the current generation.

reset

public void reset()

Resets the bestFitness parameter.