Stagnation Hypervolume Terminator
Source:R/TerminatorStagnationHypervolume.R
mlr_terminators_stagnation_hypervolume.RdClass to terminate the optimization after the hypervolume stagnates,
i.e. does not improve more than threshold over the last iters iterations.
The hypervolume is computed using moocore::hypervolume().
The reference point is the maximum of each objective over all evaluations.
Dictionary
This Terminator can be instantiated via the
dictionary mlr_terminators or with the associated
sugar function trm():
Parameters
itersinteger(1)
Number of iterations to evaluate the performance improvement on, default is 10.thresholdnumeric(1)
If the improvement is less thanthreshold, optimization is stopped, default is0.
Super class
Terminator -> TerminatorStagnationHypervolume
Methods
TerminatorStagnationHypervolume$is_terminated()
Is TRUE if the termination criterion is positive, and FALSE otherwise.
Arguments
archive(Archive).
Examples
TerminatorStagnation$new()
#>
#> ── <TerminatorStagnation> - Stagnation ─────────────────────────────────────────
#> • Parameters: iters=10, threshold=0
trm("stagnation", iters = 5, threshold = 1e-5)
#>
#> ── <TerminatorStagnation> - Stagnation ─────────────────────────────────────────
#> • Parameters: iters=5, threshold=1e-05