All Classes and Interfaces
Class
Description
A categorical parameter representing different aggregation functions used in decomposition-based
multi-objective optimization algorithms like MOEA/D.
Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using the WFG
problems as training set.A utility class for running NSGA-II with irace for automatic algorithm configuration.
Interface representing a configurable evolutionary algorithm.
Abstract base class for configurable implementations of the MOEA/D (Multi-Objective Evolutionary
Algorithm based on Decomposition) algorithm.
Base class for Multi-Objective Particle Swarm Optimization (MOPSO) algorithms.
Abstract base class for configurable NSGA-II (Non-dominated Sorting Genetic Algorithm II)
implementations.
Abstract base class for configurable NSGA-II algorithm implementations for evolutionary
algorithms.
Abstract base class for configurable SMS-EMOA (S-Metric Selection Evolutionary Multi-Objective Algorithm)
implementations for evolutionary algorithms.
Parameter class representing the configuration and factory for crossover operators for
BinarySolution in evolutionary algorithms.Configurable implementation of the MOEA/D algorithm for binary-based problems.
A parameter class for configuring binary mutation operators in evolutionary algorithms.
A configurable implementation of the Non-dominated Sorting Genetic Algorithm II (NSGA-II)
specifically designed for binary-encoded optimization problems.
Factory class for creating and configuring categorical parameters specific to evolutionary algorithms
that operate on BinarySolution individuals.
A parameter class for configuring variation operators specifically designed for binary solutions.
A parameter representing a boolean value.
A parameter representing a categorical value selected from a predefined list of valid integers.
A parameter representing a categorical value selected from a predefined list of valid values.
Processes categorical parameters from YAML configuration.
Represents a parameter that becomes active only when a specified condition is satisfied by the
value of another parameter in a multi-objective metaheuristic parameter space.
Manages a collection of
ConditionalParameter objects associated with a main parameter in
a multi-objective metaheuristic parameter space.A parameter for creating initial binary solutions in evolutionary algorithms.
A parameter for creating initial double solutions in evolutionary algorithms.
An abstract categorical parameter for creating initial solutions in evolutionary algorithms.
A parameter for creating initial permutation solutions in evolutionary algorithms.
Abstract parameter class representing a configurable crossover operator for evolutionary algorithms.
A categorical parameter representing different density estimator strategies for solutions in
multi-objective optimization.
A categorical parameter representing different Differential Evolution (DE) crossover variants.
A categorical parameter representing selection strategies for Differential Evolution (DE) algorithms.
Parameter class representing the configuration and factory for crossover operators for
DoubleSolution in evolutionary algorithms.Configurable implementation of the MOEA/D algorithm for real-coded (double) problems.
A parameter class for configuring mutation operators specifically designed for double-encoded solutions.
A configurable implementation of the Non-dominated Sorting Genetic Algorithm II (NSGA-II)
specifically designed for continuous (real-valued) optimization problems.
A parameter representing a
double value constrained within a specified inclusive range.Factory class for creating and configuring categorical parameters specific to evolutionary
algorithms that operate on DoubleSolution individuals.
Processes double/real parameters from YAML configuration.
Configurable implementation of the NSGA-II algorithm for double-valued (real-coded) problems.
Specialized selection parameter for double solutions that extends the base CategoricalParameter.
Configurable implementation of the SMS-EMOA (S-Metric Selection Evolutionary Multi-Objective Algorithm)
for double-valued (real-coded) problems.
A parameter class for configuring variation operators specifically designed for double-encoded solutions.
Interface defining the contract for different evaluation budget strategies in meta-optimization
problems.
A specialized quality indicator that tracks and returns the number of evaluations performed by an algorithm.
A builder class for creating instances of
EvolutionaryAlgorithm with optional archive support.A categorical parameter representing different external archive strategies for multi-objective optimization algorithms.
Implementation of EvaluationBudgetStrategy that uses fixed evaluation counts for each problem.
A categorical parameter representing different global best initialization strategies for Particle Swarm Optimization (PSO).
A categorical parameter representing different global best selection strategies for Particle Swarm Optimization (PSO).
A categorical parameter representing different global best update strategies for Particle Swarm Optimization (PSO).
Class that returns the negative of the hypervolume value.
A categorical parameter representing different inertia weight computing strategies for Particle Swarm Optimization (PSO).
A parameter representing an
int value constrained within a specified inclusive range.Processes integer parameters from YAML configuration.
Program to generate the irace configuration file for class
DoubleNSGAIIProgram to generate the irace configuration file for the MOEA/D algorithm with real-coded solutions.
Program to generate the irace configuration file for the MOEA/D algorithm with permutation solutions.
Program to generate the irace configuration file for the MOPSO (Multi-Objective Particle Swarm Optimization)
algorithm.
Program to generate the irace configuration file for the NSGA-II algorithm with binary solutions.
Program to generate the irace configuration file for the NSGA-II algorithm with real-coded solutions.
Program to generate the irace configuration file for the NSGA-II algorithm with permutation solutions.
A generator for creating parameter description files in the irace configuration format.
Program to generate the irace configuration file for the RDS-MOEA/D algorithm with real-coded solutions.
Program to generate the irace configuration file for the RDS-MOEA/D algorithm with permutation solutions.
A categorical parameter representing different local best initialization strategies for Particle Swarm Optimization (PSO).
A categorical parameter representing different local best update strategies for Particle Swarm Optimization (PSO).
Builder for creating asynchronous multi-threaded NSGA-II instances for optimization tasks.
Builder for creating NSGA-II instances configured for meta-optimization tasks with double
solutions.
A meta-optimization problem that optimizes the parameters of an optimization algorithm
by evaluating its performance across multiple problem instances using quality indicators.
Builder for creating SMPSO (Speed-constrained Multi-objective Particle Swarm Optimization)
instances configured for meta-optimization tasks.
Parameter space for the MOEA/D algorithm using binary solutions.
Class configuring MOEA/D using arguments in the form <key, value>
Base parameter space for the MOEA/D algorithm.
Parameter space for the MOEA/D algorithm using real-coded (double) solutions.
Class configuring MOEA/D using arguments in the form <key, value>
Parameter space for the MOEA/D algorithm using permutation-based solutions.
Factory class for creating and configuring categorical parameters specific to the MOPSO algorithm.
Parameter space configuration for Multi-Objective Particle Swarm Optimization (MOPSO) algorithms.
Abstract parameter class representing a configurable mutation operator for evolutionary algorithms.
Parameter space for NSGA-II algorithm variants using binary-coded solutions.
This class demonstrates the configuration and execution of the NSGA-II (Non-dominated Sorting Genetic Algorithm II)
for solving bi-objective Traveling Salesman Problem (TSP) instances.
This class demonstrates the configuration and execution of NSGA-II (Non-dominated Sorting Genetic Algorithm II)
for solving bi-objective Traveling Salesman Problem (TSP) instances, with additional runtime visualization.
Abstract parameter space for NSGA-II algorithm variants.
Parameter space for NSGA-II algorithm variants using real-coded (double) solutions.
Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using
the RE problems with three objectives as the training set.Class for running NSGA-II as meta-optimizer to configure
DoubleMOEAD using problem the
DTLZ problem family as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleMOEAD using
problem ZDT4 as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleMOEAD using
problem ZDT4 as training set.Class for running NSGA-II as meta-optimizer to configure
BaseMOPSO using
problem DTLZ problems as training set.Class for running NSGA-II as meta-optimizer to configure
BaseMOPSO using
problem ZDT4 as training set.Class for running NSGA-II as meta-optimizer to configure
BaseMOPSO using
problem ZDT4 as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using
problem ZDT4 as the training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using
the RE problems with three objectives as the training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using
problem ZDT4 as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using the ZDT
problems as the training set.Class for running NSGA-II as meta-optimizer to configure
PermutationNSGAII using
problem KroAB100TSP as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using problem
DTLZ3 as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using
problem RE31 as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using
problem ZDT4 as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using problem
ZDT4 as the training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using problem
ZDT4 as training set.Class for running NSGA-II as meta-optimizer to configure
PermutationNSGAII using
problem KroAB100TSP as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleNSGAII using
problem ZDT4 as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleSMSEMOA using
problem ZDT4 as training set.Class for running NSGA-II as meta-optimizer to configure
DoubleSMSEMOA using problem
ZDT4 as training set.Parameter space for NSGA-II algorithm variants using permutation-based solutions.
Example: Running NSGA-II on ZDT4 Problem
This example demonstrates how to configure and execute the NSGA-II algorithm to solve the ZDT4
multi-objective optimization problem using the Evolver framework.
Represents a configurable parameter with a value of type
T, supporting hierarchical
sub-parameters.A factory interface for creating
CategoricalParameter instances specific to different types of solutions.Interface for parameter processors that handle different types of parameters.
Abstract class that defines a configurable parameter space for metaheuristics.
A builder class for creating instances of
ParticleSwarmOptimizationAlgorithm with optional archive support.Parameter class representing the configuration and factory for crossover operators for
PermutationSolution in evolutionary algorithms.Configurable implementation of the MOEA/D algorithm for permutation-based problems.
A parameter class for configuring mutation operators specifically designed for permutation solutions.
A configurable implementation of the Non-dominated Sorting Genetic Algorithm II (NSGA-II)
specifically designed for permutation-based optimization problems.
Factory class for creating and configuring categorical parameters specific to evolutionary algorithms
that operate on permutation-based solutions.
Implementation of RDS-MOEA for permutation problems.
A parameter class for configuring variation operators specifically designed for permutation solutions.
A categorical parameter representing different perturbation strategies for Particle Swarm Optimization (PSO).
A categorical parameter representing different position update strategies for Particle Swarm Optimization (PSO).
A specialized DoubleParameter that represents a probability value between 0.0 and 1.0 (inclusive).
Interface defining methods for returning information about problem families, including a list with their
implementations, a list with the names of the reference fronts, and a list containing the typical number
of evaluations used to optimize them by metaheuristics.
Implementation of EvaluationBudgetStrategy that generates random evaluation counts within a specified range.
A generic parameter class for numeric values constrained within an inclusive range
[lowerBound, upperBound].A categorical parameter representing different ranking strategies for solutions in multi-objective optimization.
Abstract parameter space for RDS-MOEA (Ranking and Density Selection Multi-Objective Evolutionary
Algorithm) variants.
Parameter space for RDS-MOEA with double-encoded solutions.
Parameter space for NSGA-II algorithm variants using permutation-based solutions.
Class implementing the interface ProblemFamilyInfo for the RE problems having three objective functions.
A categorical parameter representing different repair strategies for double-solution variables
that fall outside their defined bounds.
A categorical parameter representing different replacement strategies in evolutionary algorithms.
A categorical parameter representing different selection strategies for evolutionary algorithms.
A categorical parameter representing different sequence generation strategies.
Class for running SMPSO as meta-optimizer to configure
DoubleNSGAII using
problem RE31 as training set.Abstract parameter class representing a configurable variation operator in evolutionary algorithms.
A categorical parameter representing different velocity initialization strategies for Particle Swarm Optimization (PSO).
A categorical parameter representing different velocity update strategies for Particle Swarm Optimization (PSO).
This observer stores a solution list in files.
A YAML-based parameter space implementation that loads multi-objective metaheuristic
parameter configurations from YAML files.