target.evaluator.default: target.evaluator.default
In MLopez-Ibanez/iracelhs: Iterated Racing for Automatic Algorithm Configuration

Description Usage Arguments Value Author(s)

target.evaluator.default is the default targetEvaluator function that is invoked if targetEvaluator is a string (by default targetEvaluator is NULL and this function is not invoked). You can use it as an advanced example of how to create your own targetEvaluator function.

1 2	target.evaluator.default(experiment, num.configurations, all.conf.id, scenario, target.runner.call)

`experiment`	A list describing the experiment. It contains at least: id.configurationAn alphanumeric string that uniquely identifies a configuration; id.instanceAn alphanumeric string that uniquely identifies a pair (instance, seed); seedSeed for the random number generator to be used for this evaluation, ignore the seed for deterministic algorithms; instanceString giving the instance to be used for this evaluation; extra.paramsUser-defined parameters associated to the instance; configuration1-row data frame with a column per parameter name; switchesVector of parameter switches (labels) in the order of parameters used in `configuration`.
`num.configurations`	is the number of configurations alive in the race;
`all.conf.id`	is the vector of configuration IDs of the alive configurations;
`scenario`	options passed when invoking irace;
`target.runner.call`	a string describing the call to `targetRunner` that corresponds to this call to `targetEvaluator`. This is used for providing extra information to the user, for example, in case `targetEvaluator` fails.

The function targetEvaluator must return a list with one element "cost", the numerical value corresponding to the cost measure of the given configuration on the given instance.

The return list may also contain the following optional elements that are used by irace for reporting errors in targetEvaluator:

erroris a string used to report an error;
outputRawis a string used to report the raw output of calls to an external program or function;
callis a string used to report how targetEvaluator called an external program or function.

Manuel López-Ibáñez and Jérémie Dubois-Lacoste

MLopez-Ibanez/iracelhs documentation built on May 15, 2019, 1:57 a.m.