Skip to main content

RVEATensor

Module: opytimizer.optimizers.multi_objective.evolutionary.rvea

Backend-agnostic (NumPy/CuPy) tensorized implementation of RVEA.

Constructor​

RVEATensor(params: Optional[Dict[str, Any]] = None, crossover_operator=None, mutation_operator=None, reference_vectors: numpy.ndarray = None, max_generations: int = 250, alpha: Union[float, int] = 2.0, fr: float = 0.1)

Parameters​

ParameterTypeDefaultDescription
paramsOptional[Dict[str, Any]]None—
crossover_operatorNone—
mutation_operatorNone—
reference_vectorsnumpy.ndarrayNone—
max_generationsint250—
alphaUnion[float, int]2.0—
frfloat0.1—

Methods​

compile​

compile(self, space: opytimizer.core.space._MultiObjectiveSpace)

Compiles additional information that is used by this optimizer.

This method is called before the optimization procedure and makes sure that the additional variable is available as a property.

Parameters​

ParameterTypeDefaultDescription
spaceopytimizer.core.space._MultiObjectiveSpace—

evaluate​

evaluate(self, space: opytimizer.core.space._MultiObjectiveTensorSpace, function: opytimizer.core.function.Function) -> None

Evaluates the search space according to the objective function.

Parameters​

ParameterTypeDefaultDescription
spaceopytimizer.core.space._MultiObjectiveTensorSpaceA Space object that will be evaluated.
functionopytimizer.core.function.FunctionA Function object serving as an objective function.

update​

update(self, space: opytimizer.core.space._MultiObjectiveTensorSpace, function: opytimizer.core.function.Function) -> None

Updates the agents' position array.

As each child has a different procedure of update, you will need to implement it directly on its class.

Parameters​

ParameterTypeDefaultDescription
spaceopytimizer.core.space._MultiObjectiveTensorSpace—
functionopytimizer.core.function.Function—