Terminator that stops when optimization does not improve

Description

Class to terminate the optimization after the performance stagnates, i.e. does not improve more than threshold over the last n batches.

Dictionary

This Terminator can be instantiated via the dictionary mlr_terminators or with the associated sugar function trm():

mlr_terminators$get("stagnation_batch")
trm("stagnation_batch")

Parameters

n

integer(1)
Number of batches to evaluate the performance improvement on, default is 1.

threshold

numeric(1)
If the improvement is less than threshold, optimization is stopped, default is 0.

Super class

bbotk::Terminator -> TerminatorStagnationBatch

Methods

Public methods

• TerminatorStagnationBatch$new()

• TerminatorStagnationBatch$is_terminated()

• TerminatorStagnationBatch$clone()

Method new()

Creates a new instance of this R6 class.

Usage

TerminatorStagnationBatch$new()

Method is_terminated()

Is TRUE iff the termination criterion is positive, and FALSE otherwise.

Usage

TerminatorStagnationBatch$is_terminated(archive)

Arguments

Returns

logical(1).

Method clone()

The objects of this class are cloneable with this method.

Usage

TerminatorStagnationBatch$clone(deep = FALSE)

Arguments

See Also

Other Terminator: Terminator, mlr_terminators_clock_time, mlr_terminators_combo, mlr_terminators_evals, mlr_terminators_none, mlr_terminators_perf_reached, mlr_terminators_run_time, mlr_terminators_stagnation, mlr_terminators

Examples

TerminatorStagnationBatch$new()
trm("stagnation_batch", n = 1, threshold = 1e-5)