mlr3tuning (version 0.1.0)

TunerRandomSearch: TunerRandomSearch

Description

Subclass for random search tuning.

The random points are sampled by paradox::generate_design_random().

In order to support general termination criteria and parallelization, we evaluate points in a batch-fashion of size batch_size. Larger batches mean we can parallelize more, smaller batches imply a more fine-grained checking of termination criteria.

Arguments

Format

R6::R6Class object inheriting from Tuner.

Construction

TunerRandomSearch$new(batch_size = 1L)
tnr("random_search")

Parameters

  • batch_size :: integer(1) Maximum number of configurations to try in a batch.

See Also

Other Tuner: TunerDesignPoints, TunerGenSA, TunerGridSearch, Tuner, mlr_tuners

Examples

Run this code
# NOT RUN {
# see ?Tuner
# }

Run the code above in your browser using DataLab