return ``pheno(self.mean - (geno(x) - self.mean))``. TODO: this implementation is yet experimental. Selectively mirrored samplin

return the set of indices to be reevaluted for noise measurement, taking the ``lam_reeval`` best from the first ``2 * lam_reeval + 2``

(re-)set to the initial state

reset logger, overwrite original files, `modulo`: log only every modulo call

reset logger, overwrite original files, `modulo`: log only every modulo call

This fn runs in a new process. Now we are going to do a little bookkeeping and then spin off the actual job that does whatever it is we're tr

loads data from files written and return a data dictionary, *not* a prerequisite for using `plot()` or `disp()`. Argument `filenam

loads data from files written and return a data dictionary, *not* a prerequisite for using `plot()` or `disp()`. Argument `filenam

to install and/or test from the command line use:: python cma.py [options | func dim sig0 [optkey optval][optkey optval]...] --test

multiply C with a scalar and update all related internal variables (dC, D,...)

plot data from a `CMADataLogger` (using the files written by the logger). Arguments --------- `fig`

helper function for `plot()` that plots all what is in the upper left subplot like fitness, sigma, etc. Arguments -------

helper function for `plot()` that plots all what is in the upper left subplot like fitness, sigma, etc. Arguments -------

Redirect stdout and stderr to a file.

store two fitness lists, `fit` and ``fitre`` reevaluating some solutions in `X`. ``self.evaluations`` evaluations are done for each

register a `CMAEvolutionStrategy` instance for logging, ``append=True`` appends to previous data logged under the same name, by defa

return ``(xbest, f(xbest), evaluations_xbest, evaluations, iterations, pheno(xmean), effective_stds)``

Rosenbrock test objective function

Run it as a Matlab function.

Run a compiled Matlab job.

Run a Python function.

Run a torch based job.

save to file

Compute strategy parameters as a function of dimension and population size

return stochastic round: floor(nb) + (rand()<remainder(nb))

Start the web view in a separate process.

abstract method, AKA "update", prepare for next iteration

update

adapt self.evaluations depending on the current measurement value and return ``sigma_fac in (1.0, self.alphasigma)``

update internal variables for sampling the distribution with the current covariance matrix C. This method is O(N^3), if C is not diagonal.

exponential update of C that guarantees positive definiteness, that is, instead of the assignment ``C = C + eta * Z``, C gets C**.5

updated noise level measure using two fitness lists ``self.fit`` and ``self.fitre``, return ``self.noiseS, all_individual_measures``.