saealib.GenomeGA

class saealib.GenomeGA(crossover, mutation, parent_selection, survivor_selection)

Bases: AskTellAlgorithm

A small ask/tell GA that only uses the GenomeBatch protocol.

Parameters:

• crossover (object)

• mutation (object)

• parent_selection (ParentSelection)

• survivor_selection (SurvivorSelection)

Methods

__init__
ask	Generate offspring from the current optimization state.
contract	Return the component contract for this genetic algorithm.
create_pareto_archive	Create a ParetoArchive with the correct direction for the problem.
get_required_attrs	Return population attributes required by this algorithm.
tell	Update the population with evaluated offspring.

Method Details

GenomeGA.__init__(crossover, mutation, parent_selection, survivor_selection)

Parameters:

• crossover (object)

• mutation (object)

• parent_selection (ParentSelection)

• survivor_selection (SurvivorSelection)

Return type:

None

GenomeGA.ask(request, state)

Generate offspring from the current optimization state.

Parameters:

• request (ProposalRequest)

• state (StateView)

Return type:

ProposalBatch

GenomeGA.contract()

Return the component contract for this genetic algorithm.

GenomeGA.create_pareto_archive(attrs, init_capacity, problem)

Create a ParetoArchive with the correct direction for the problem.

Parameters:

• attrs (list[PopulationAttribute])

• init_capacity (int)

• problem (Problem)

Return type:

ParetoArchive

GenomeGA.get_required_attrs(problem)

Return population attributes required by this algorithm.

Parameters:

problem (Problem)

Return type:

list[PopulationAttribute]

GenomeGA.tell(feedback, state)

Update the population with evaluated offspring.

Parameters:

• feedback (FeedbackBatch)

• state (StateView)

Return type:

StatePatch