SMSEMOEA

Type Members

type A = None.type

Definition Classes
NoArchive → Archive → A
case class EvolutionState(population: Population[Evolution.G, Evolution.P, Evolution.F, Evolution.MF], archive: Evolution.A, generation: Int, terminationState: Evolution.STATE, terminated: Boolean) extends Product with Serializable

Represent a state of the evolution algorithm
Represent a state of the evolution algorithm

Definition Classes
Evolution
abstract type F

Definition Classes
F
type G = Genome

Definition Classes
GAGenomeWithSigmaType → G
type MF = Rank

the type of the meta-fitness
the type of the meta-fitness

Definition Classes
RankModifier → MF
abstract type P

Definition Classes
P
abstract type STATE

Type of the state maintained to study the evolution of the algorithm
Type of the state maintained to study the evolution of the algorithm

Definition Classes
Termination

Abstract Value Members

abstract def fitness: SimpleLens[F, Seq[Double]]

Definition Classes
MG
abstract def genomeSize: Int

Size of the value part of the genome
Size of the value part of the genome

Definition Classes
GA
abstract def initialState: STATE

Compute the initial state
Compute the initial state
returns
the initial state

Definition Classes
Termination
abstract def lambda: Int

the size of the offspring
the size of the offspring

Definition Classes
Lambda
abstract def mu: Int

the size of the population
the size of the population

Definition Classes
Mu
abstract def referencePoint: Seq[Double]

value of the reference point for the hypervolume computation
value of the reference point for the hypervolume computation

Definition Classes
ReferencePoint
abstract def terminated(population: ⇒ Population[G, P, F, MF], terminationState: STATE): (Boolean, STATE)

Test if the algorithm has converged.
Test if the algorithm has converged.
population
the current population
terminationState
the actual termination state
returns
a boolean which is equal to true if a terminal state has been detected and the new termination state

Definition Classes
Termination

Concrete Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def archive(a: A, individuals: Seq[Individual[G, P, F]]): A

Definition Classes
Archive
final def asInstanceOf[T0]: T0

Definition Classes
Any
def breed(individuals: Seq[Individual[G, P, F]], a: A, size: Int)(implicit rng: Random): Seq[G]

Breed genomes from a population
Breed genomes from a population
individuals
the population from which genomes are breeded
size
the size of the breeded set
returns
the breeded genomes

Definition Classes
GeneticBreeding → Breeding
def buildRNG(seed: Long): Random

Definition Classes
Evolution
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def cloneProbability: Double

Definition Classes
GeneticBreeding
def combine(a1: A, a2: A): None.type

Definition Classes
NoArchive → Archive
def computeHypervolume(front: IndexedSeq[(Seq[Double], Int)], referencePoint: Seq[Double]): IndexedSeq[(Lazy[Double], Int)]

Compute the hypervolume contribution for each front
Compute the hypervolume contribution for each front

Definition Classes
HypervolumeDiversity
def crossover(g1: G, g2: G, population: Seq[Individual[G, P, F]], archive: A)(implicit rng: Random): Seq[G]

Crossover g1 and g2
Crossover g1 and g2
g1
a genome
g2
another genome
population
last computed population
archive
last archive
returns
the result of the crossover

Definition Classes
SBXBoundedCrossover → Crossover
def crossoverRate: Double

crossover rate parameter of the algorithm
crossover rate parameter of the algorithm

Definition Classes
CrossoverRate
def diff(original: A, modified: A): None.type

Definition Classes
NoArchive → Archive
def distributionIndex: Double

distribution index parameter of the algorithm
distribution index parameter of the algorithm

Definition Classes
SBXBoundedCrossover
def diversity(values: Seq[Seq[Double]]): Seq[Lazy[Double]]

Compute the diversity metric of the values
Compute the diversity metric of the values
values
a set of values
returns
a diversity sequence in the diversity of the individual i at the position i

Definition Classes
HypervolumeDiversity → DiversityMetric
def elitism(individuals: Seq[Individual[G, P, F]], archive: A)(implicit rng: Random): Seq[Individual[G, P, F]]

Reduce the number of elements of the population and return a new one
Reduce the number of elements of the population and return a new one
individuals
the population to shrink
returns
the shrinked population

Definition Classes
RankElitism → MergedGenerations
def elitism(oldGeneration: Seq[Individual[G, P, F]], newGeneration: Seq[Individual[G, P, F]], archive: A)(implicit aprng: Random): Seq[Individual[G, P, F]]

Definition Classes
MergedGenerations → Elitism
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def evolve(expression: (G, Random) ⇒ P, evaluation: (P, Random) ⇒ F)(implicit prng: Random): Iterator[EvolutionState]

Run the evolutionary algorithm
Run the evolutionary algorithm
expression
the genome expression
evaluation
the fitness evaluator
returns
an iterator over the states of the evolution

Definition Classes
Evolution
def evolve(individuals: Seq[Individual[G, P, F]], a: A, expression: (G, Random) ⇒ P, evaluation: (P, Random) ⇒ F)(implicit aprng: Random): Iterator[EvolutionState]

Run the evolutionary algorithm
Run the evolutionary algorithm
individuals
the initial individuals
expression
the genome expression
evaluation
the fitness evaluator
returns
an iterator over the states of the evolution

Definition Classes
Evolution
def filter(individuals: Seq[Individual[G, P, F]]): Seq[Individual[G, P, F]]

Filter the individuals
Filter the individuals
individuals
the set of evaluated individuals
returns
the filtrated individuals

Definition Classes
IndividualFilter
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def fitnesses(evaluated: Seq[Individual[G, P, F]], archive: A): Seq[Seq[Double]]

Definition Classes
RankOnDiversity → ModifiedFitness
def genome: SimpleLens[G, Seq[Double]]

The entire genome with potentially additional information
The entire genome with potentially additional information

Definition Classes
GAGenomeWithSigma → GA
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
def initialArchive: A

Definition Classes
NoArchive → Archive
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def minimumSigma: Double

Definition Classes
CoEvolvingSigmaValuesMutation
def modify(evaluated: Seq[Individual[G, P, F]], archive: A): Population[G, P, F, MF]

Generate a population from a set of indiviuals
Generate a population from a set of indiviuals
returns
the population with the meta-fitness for each individual

Definition Classes
RankModifier → Modifier
def mutate(genome: G, population: Seq[Individual[G, P, F]], archive: A)(implicit rng: Random): G

Mutate a genome
Mutate a genome
genome
genome to mutate
population
the last computed population
archive
the last archive
rng
a random number geneartor
returns
the mutated genome

Definition Classes
CoEvolvingSigmaValuesMutation → Mutation
def mutationRate: Double

Definition Classes
MutationRate
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def randomGenome(implicit rng: Random): Genome

Definition Classes
GAGenomeWithSigma → GA → RandomGenome
def rank(values: Seq[Seq[Double]]): Seq[Lazy[Int]]

Compute the rank of a set of individuals.
Compute the rank of a set of individuals.
values
the values to rank
returns
the ranks of the individuals in the same order

Definition Classes
HierarchicalRanking → Ranking
def rank: Lens[MF, MF, Lazy[Int], Lazy[Int]]

Definition Classes
RankModifier → RankMF
def sbxCrossover(g1: G, g2: G)(implicit rng: Random): (G, G)

Definition Classes
SBXBoundedCrossover
def selectOne(population: Population[G, P, F, MF])(implicit rng: Random): Individual[G, P, F]

Definition Classes
BinaryTournamentSelection → OneByOne
def selection(population: Population[G, P, F, MF])(implicit aprng: Random): Iterator[Individual[G, P, F]]

Select an individual among the population.
Select an individual among the population.
population
the population in which selection occurs
returns
the selected individual

Definition Classes
OneByOne → Selection
def sigma: Lens[G, G, Seq[Double], Seq[Double]]

Definition Classes
GAGenomeWithSigma → Sigma
def step(individuals: Seq[Individual[G, P, F]], archive: A, expression: (G, Random) ⇒ P, evaluation: (P, Random) ⇒ F)(implicit rng: Random): (Seq[Individual[G, P, F]], A)

Evolve one step
Evolve one step
individuals
the current population
archive
the current archive
expression
expression of the genome
evaluation
the fitness evaluator
returns
a new population of evaluated solutions

Definition Classes
Evolution
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toArchive(individuals: Seq[Individual[G, P, F]]): A

Definition Classes
NoArchive → Archive
def toPopulation(individuals: Seq[Individual[G, P, F]], a: A): Population[G, P, F, MF]

Generate a population from a set of indiviuals that is filtered in a first time
Generate a population from a set of indiviuals that is filtered in a first time
individuals
a set of individual
returns
the filtred population with the meta-fitness for each individual

Definition Classes
Modifier
def toString(): String

Definition Classes
AnyRef → Any
def tournament(e1: PopulationElement[G, P, F, MF], e2: PopulationElement[G, P, F, MF])(implicit rng: Random): PopulationElement[G, P, F, MF]

Select the best ranked and if equal the more diverse individual between two population elements.
Select the best ranked and if equal the more diverse individual between two population elements.
e1
the first population element
e2
the second population element
returns
the winning population element

Definition Classes
TournamentOnRank → Tournament
def values: Lens[G, G, Seq[Double], Seq[Double]]

The value part of the genome actually used for the optimisation
The value part of the genome actually used for the optimisation

Definition Classes
GAGenomeWithSigma → GA
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

trait SMSEMOEA extends Evolution with GAGenomeWithSigma with MG with BinaryTournamentSelection with TournamentOnRank with RankModifier with RankOnDiversity with RankElitism with CoEvolvingSigmaValuesMutation with SBXBoundedCrossover with HypervolumeDiversity with NoArchive with GeneticBreeding

Type Members

type A = None.type

case class EvolutionState(population: Population[Evolution.G, Evolution.P, Evolution.F, Evolution.MF], archive: Evolution.A, generation: Int, terminationState: Evolution.STATE, terminated: Boolean) extends Product with Serializable

abstract type F

type G = Genome

type MF = Rank

abstract type P

abstract type STATE

Abstract Value Members

abstract def fitness: SimpleLens[F, Seq[Double]]

abstract def genomeSize: Int

abstract def initialState: STATE

abstract def lambda: Int

abstract def mu: Int

abstract def referencePoint: Seq[Double]

abstract def terminated(population: ⇒ Population[G, P, F, MF], terminationState: STATE): (Boolean, STATE)

Concrete Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def archive(a: A, individuals: Seq[Individual[G, P, F]]): A

final def asInstanceOf[T0]: T0

def breed(individuals: Seq[Individual[G, P, F]], a: A, size: Int)(implicit rng: Random): Seq[G]

def buildRNG(seed: Long): Random

def clone(): AnyRef

def cloneProbability: Double

def combine(a1: A, a2: A): None.type

def computeHypervolume(front: IndexedSeq[(Seq[Double], Int)], referencePoint: Seq[Double]): IndexedSeq[(Lazy[Double], Int)]

def crossover(g1: G, g2: G, population: Seq[Individual[G, P, F]], archive: A)(implicit rng: Random): Seq[G]

def crossoverRate: Double

def diff(original: A, modified: A): None.type

def distributionIndex: Double

def diversity(values: Seq[Seq[Double]]): Seq[Lazy[Double]]

def elitism(individuals: Seq[Individual[G, P, F]], archive: A)(implicit rng: Random): Seq[Individual[G, P, F]]

def elitism(oldGeneration: Seq[Individual[G, P, F]], newGeneration: Seq[Individual[G, P, F]], archive: A)(implicit aprng: Random): Seq[Individual[G, P, F]]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def evolve(expression: (G, Random) ⇒ P, evaluation: (P, Random) ⇒ F)(implicit prng: Random): Iterator[EvolutionState]

def evolve(individuals: Seq[Individual[G, P, F]], a: A, expression: (G, Random) ⇒ P, evaluation: (P, Random) ⇒ F)(implicit aprng: Random): Iterator[EvolutionState]

def filter(individuals: Seq[Individual[G, P, F]]): Seq[Individual[G, P, F]]

def finalize(): Unit

def fitnesses(evaluated: Seq[Individual[G, P, F]], archive: A): Seq[Seq[Double]]

def genome: SimpleLens[G, Seq[Double]]

final def getClass(): Class[_]

def hashCode(): Int

def initialArchive: A

final def isInstanceOf[T0]: Boolean

def minimumSigma: Double

def modify(evaluated: Seq[Individual[G, P, F]], archive: A): Population[G, P, F, MF]

def mutate(genome: G, population: Seq[Individual[G, P, F]], archive: A)(implicit rng: Random): G

def mutationRate: Double

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def randomGenome(implicit rng: Random): Genome

def rank(values: Seq[Seq[Double]]): Seq[Lazy[Int]]

def rank: Lens[MF, MF, Lazy[Int], Lazy[Int]]

def sbxCrossover(g1: G, g2: G)(implicit rng: Random): (G, G)

def selectOne(population: Population[G, P, F, MF])(implicit rng: Random): Individual[G, P, F]

def selection(population: Population[G, P, F, MF])(implicit aprng: Random): Iterator[Individual[G, P, F]]

def sigma: Lens[G, G, Seq[Double], Seq[Double]]

def step(individuals: Seq[Individual[G, P, F]], archive: A, expression: (G, Random) ⇒ P, evaluation: (P, Random) ⇒ F)(implicit rng: Random): (Seq[Individual[G, P, F]], A)

final def synchronized[T0](arg0: ⇒ T0): T0

def toArchive(individuals: Seq[Individual[G, P, F]]): A

def toPopulation(individuals: Seq[Individual[G, P, F]], a: A): Population[G, P, F, MF]

def toString(): String

def tournament(e1: PopulationElement[G, P, F, MF], e2: PopulationElement[G, P, F, MF])(implicit rng: Random): PopulationElement[G, P, F, MF]

def values: Lens[G, G, Seq[Double], Seq[Double]]

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from breed.GeneticBreeding

Inherited from archive.NoArchive

Inherited from diversity.HypervolumeDiversity

Inherited from metric.ReferencePoint

Inherited from crossover.SBXBoundedCrossover

Inherited from CrossoverRate

Inherited from Crossover