AbstractWModel#

class ioh.iohcpp.problem.AbstractWModel(self: ioh.iohcpp.problem.AbstractWModel, problem_id: int, instance: int, n_variables: int, name: str, dummy_select_rate: float = 0.0, epistasis_block_size: int = 0, neutrality_mu: int = 0, ruggedness_gamma: int = 0)#

Bases: IntegerSingleObjective

An abstract W-model class. Please apply the WModelOneMax and WModelLeadingOnes classes.

W-model problems applies four basic transformations: reduction of dummy variables, neutrality, epistasis, and fitness perturbation on benchmark problems. Each transformation is configured by the corresponding argument dummy_select_rate, epistasis_block_size, neutrality_mu, and ruggedness_gamma.

The details of the transformations can be found in https://www.sciencedirect.com/science/article/pii/S1568494619308099

We have acknowledged Thomas Weise, proposing the original W-model https://dl.acm.org/doi/abs/10.1145/3205651.3208240 and having discussions supporting this work.

Reference#

[WeiseW18] Thomas Weise and Zijun Wu. “Difficult features of combinatorial optimization problems and the tunable w-model benchmark problem for simulating them.” Proc. of the Genetic and Evolutionary Computation Conference Companion, 1769-1776, 2018

[DoerrYHWSB20] Carola Doerr, Furong Ye, Naama Horesh, Hao Wang, Ofer M. Shir, Thomas Bäck. “Benchmarking discrete optimization heuristics with IOHprofiler.” Applied Soft Computing, 88: 106027, 2020

Attributes Summary

`bounds`	The bounds of the problem.
`constraints`	The constraints of the problem.
`log_info`	The data is that being sent to the logger.
`meta_data`	The static meta-data of the problem containing, e.g., problem id, instance id, and problem's dimensionality
`optimum`	The optimum and its objective value for a problem instance
`problems`
`state`	The current state of the optimization process containing, e.g., the current solution and the number of function evaluated consumed so far

Methods Summary

`__call__`	Evaluate the problem.
`add_constraint`	add a constraint
`attach_logger`	Attach a logger to the problem to allow performance tracking.
`create`	Create a problem instance
`detach_logger`	Remove the specified logger from the problem.
`enforce_bounds`	Enforced the bounds (box-constraints) as constraint :param weight: :type weight: The weight for computing the penalty (can be infinity to have strict box-constraints) :param how: :type how: The enforcement strategy, should be one of the 'ioh.ConstraintEnforcement' options :param exponent: :type exponent: The exponent for scaling the contraint
`remove_constraint`	remove a constraint
`reset`	Reset all state variables of the problem.
`set_id`	update the problem id
`set_instance`	update the problem instance
`set_name`	update the problem name
`wmodel_evaluate`(self, arg0)

Attributes Documentation

bounds#: The bounds of the problem.

constraints#: The constraints of the problem.

log_info#: The data is that being sent to the logger.

meta_data#: The static meta-data of the problem containing, e.g., problem id, instance id, and problem’s dimensionality

optimum#: The optimum and its objective value for a problem instance

problems#

state#: The current state of the optimization process containing, e.g., the current solution and the number of function evaluated consumed so far

Methods Documentation

__call__()#

Evaluate the problem.

Parameters:: x (list) – the search point to evaluate. It must be a 1-dimensional array/list whose length matches search space’s dimensionality
Returns:: The evaluated search point
Return type:: float

Evaluate the problem.

Parameters:: x (list[list]) – the search points to evaluate. It must be a 2-dimensional array/list whose length matches search space’s dimensionality
Returns:: The evaluated search points
Return type:: list[float]

add_constraint()#: add a constraint

attach_logger()#

Attach a logger to the problem to allow performance tracking.

Parameters:: logger (Logger) – A logger-object from the IOHexperimenter logger module.

static create()#

Create a problem instance

Parameters:

problem_name (a string indicating the problem name.) –
instance_id (an integer identifier of the problem instance, which seeds the random generation) – of the tranformations in the search/objective spaces
dimension (integer, representing the dimensionality of the search space) –

Create a problem instance

Parameters:

problem_id (the index of the problem to create.) –
instance_id (an integer identifier of the problem instance, which seeds the random generation) – of the tranformations in the search/objective spaces
dimension (integer, representing the dimensionality of the search space) –

detach_logger()#: Remove the specified logger from the problem.

enforce_bounds()#: Enforced the bounds (box-constraints) as constraint :param weight: :type weight: The weight for computing the penalty (can be infinity to have strict box-constraints) :param how: :type how: The enforcement strategy, should be one of the ‘ioh.ConstraintEnforcement’ options :param exponent: :type exponent: The exponent for scaling the contraint

remove_constraint()#: remove a constraint

reset()#: Reset all state variables of the problem.

set_id()#: update the problem id

set_instance()#: update the problem instance

set_name()#: update the problem name

wmodel_evaluate(self: ioh.iohcpp.problem.AbstractWModel, arg0: List[int]) → int#