moeoIBEA< MOEOT > Class Template Reference

IBEA (Indicator-Based Evolutionary Algorithm) as described in: E. More...

#include <moeoIBEA.h>

Inheritance diagram for moeoIBEA< MOEOT >:

List of all members.

Public Types
typedef MOEOT::ObjectiveVector	ObjectiveVector
	The type of objective vector.
Public Member Functions
	moeoIBEA (unsigned int _maxGen, eoEvalFunc< MOEOT > &_eval, eoGenOp< MOEOT > &_op, moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &_metric, const double _kappa=0.05)
	Simple ctor with a eoGenOp.
	moeoIBEA (unsigned int _maxGen, eoEvalFunc< MOEOT > &_eval, eoTransform< MOEOT > &_op, moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &_metric, const double _kappa=0.05)
	Simple ctor with a eoTransform.
	moeoIBEA (unsigned int _maxGen, eoEvalFunc< MOEOT > &_eval, eoQuadOp< MOEOT > &_crossover, double _pCross, eoMonOp< MOEOT > &_mutation, double _pMut, moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &_metric, const double _kappa=0.05)
	Ctor with a crossover, a mutation and their corresponding rates.
	moeoIBEA (eoContinue< MOEOT > &_continuator, eoEvalFunc< MOEOT > &_eval, eoGenOp< MOEOT > &_op, moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &_metric, const double _kappa=0.05)
	Ctor with a continuator (instead of _maxGen) and a eoGenOp.
	moeoIBEA (eoContinue< MOEOT > &_continuator, eoEvalFunc< MOEOT > &_eval, eoTransform< MOEOT > &_op, moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &_metric, const double _kappa=0.05)
	Ctor with a continuator (instead of _maxGen) and a eoTransform.
virtual void	operator() (eoPop< MOEOT > &_pop)
	Apply a few generation of evolution to the population _pop until the stopping criteria is verified.
Protected Attributes
eoGenContinue< MOEOT >	defaultGenContinuator
	a continuator based on the number of generations (used as default)
eoContinue< MOEOT > &	continuator
	stopping criteria
eoPopLoopEval< MOEOT >	popEval
	evaluation function used to evaluate the whole population
moeoDetTournamentSelect< MOEOT >	select
	binary tournament selection
moeoIndicatorBasedFitnessAssignment< MOEOT >	fitnessAssignment
	fitness assignment used in IBEA
moeoDummyDiversityAssignment< MOEOT >	dummyDiversityAssignment
	dummy diversity assignment
moeoEnvironmentalReplacement< MOEOT >	replace
	elitist replacement
eoSGAGenOp< MOEOT >	defaultSGAGenOp
	an object for genetic operators (used as default)
eoGeneralBreeder< MOEOT >	genBreed
	general breeder
eoBreed< MOEOT > &	breed
	breeder

---

Detailed Description

template<class MOEOT>
class moeoIBEA< MOEOT >

IBEA (Indicator-Based Evolutionary Algorithm) as described in: E.

Zitzler, S. Künzli, "Indicator-Based Selection in Multiobjective Search", Proc. 8th International Conference on Parallel Problem Solving from Nature (PPSN VIII), pp. 832-842, Birmingham, UK (2004). This class builds the IBEA algorithm only by using the fine-grained components of the ParadisEO-MOEO framework.

Definition at line 38 of file moeoIBEA.h.

---

Constructor & Destructor Documentation

template<class MOEOT>

moeoIBEA< MOEOT >::moeoIBEA	(	unsigned int	_maxGen,
		eoEvalFunc< MOEOT > &	_eval,
		eoGenOp< MOEOT > &	_op,
		moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &	_metric,
		const double	_kappa = 0.05
	)			[inline]

Simple ctor with a eoGenOp.

Parameters:

	_maxGen	number of generations before stopping
	_eval	evaluation function
	_op	variation operator
	_metric	metric
	_kappa	scaling factor kappa

Definition at line 54 of file moeoIBEA.h.

template<class MOEOT>

moeoIBEA< MOEOT >::moeoIBEA	(	unsigned int	_maxGen,
		eoEvalFunc< MOEOT > &	_eval,
		eoTransform< MOEOT > &	_op,
		moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &	_metric,
		const double	_kappa = 0.05
	)			[inline]

Simple ctor with a eoTransform.

Parameters:

	_maxGen	number of generations before stopping
	_eval	evaluation function
	_op	variation operator
	_metric	metric
	_kappa	scaling factor kappa

Definition at line 68 of file moeoIBEA.h.

template<class MOEOT>

moeoIBEA< MOEOT >::moeoIBEA	(	unsigned int	_maxGen,
		eoEvalFunc< MOEOT > &	_eval,
		eoQuadOp< MOEOT > &	_crossover,
		double	_pCross,
		eoMonOp< MOEOT > &	_mutation,
		double	_pMut,
		moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &	_metric,
		const double	_kappa = 0.05
	)			[inline]

Ctor with a crossover, a mutation and their corresponding rates.

Parameters:

	_maxGen	number of generations before stopping
	_eval	evaluation function
	_crossover	crossover
	_pCross	crossover probability
	_mutation	mutation
	_pMut	mutation probability
	_metric	metric
	_kappa	scaling factor kappa

Definition at line 85 of file moeoIBEA.h.

template<class MOEOT>

moeoIBEA< MOEOT >::moeoIBEA	(	eoContinue< MOEOT > &	_continuator,
		eoEvalFunc< MOEOT > &	_eval,
		eoGenOp< MOEOT > &	_op,
		moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &	_metric,
		const double	_kappa = 0.05
	)			[inline]

Ctor with a continuator (instead of _maxGen) and a eoGenOp.

Parameters:

	_continuator	stopping criteria
	_eval	evaluation function
	_op	variation operator
	_metric	metric
	_kappa	scaling factor kappa

Definition at line 100 of file moeoIBEA.h.

template<class MOEOT>

moeoIBEA< MOEOT >::moeoIBEA	(	eoContinue< MOEOT > &	_continuator,
		eoEvalFunc< MOEOT > &	_eval,
		eoTransform< MOEOT > &	_op,
		moeoNormalizedSolutionVsSolutionBinaryMetric< ObjectiveVector, double > &	_metric,
		const double	_kappa = 0.05
	)			[inline]

Ctor with a continuator (instead of _maxGen) and a eoTransform.

Parameters:

	_continuator	stopping criteria
	_eval	evaluation function
	_op	variation operator
	_metric	metric
	_kappa	scaling factor kappa

Definition at line 114 of file moeoIBEA.h.

---

Member Function Documentation

template<class MOEOT>

virtual void moeoIBEA< MOEOT >::operator()

(

eoPop< MOEOT > &

_pop

)

[inline, virtual]

Apply a few generation of evolution to the population _pop until the stopping criteria is verified.

Parameters:

_pop

the population

Definition at line 124 of file moeoIBEA.h.

References moeoIBEA< MOEOT >::breed, moeoIBEA< MOEOT >::continuator, moeoIBEA< MOEOT >::dummyDiversityAssignment, moeoIBEA< MOEOT >::fitnessAssignment, moeoIBEA< MOEOT >::popEval, and moeoIBEA< MOEOT >::replace.

---

The documentation for this class was generated from the following file:

• moeoIBEA.h

---