comocma.como.CmaKernel(cma.CMAEvolutionStrategy)
class documentationcomocma.como
(View In Hierarchy)
cma.CMAEvolutionStrategy
class, by adding the property
incumbent
, the attributes objective_values
and _last_offspring_f_values
.Method | __init__ | No summary |
Method | incumbent | it gives the 'repaired' mean of a cma-es. For a problem with bound constraints, self.incumbent in inside the bounds. |
Method | _copy_light | tentative copy of self, versatile (interface and functionalities may change). |
x0
initial solution, starting point. x0
is given as "phenotype"
which means, if:
opts = {'transformation': [transform, inverse]}
is given and inverse is None, the initial mean is not
consistent with x0
in that transform(mean) does not
equal to x0
unless transform(mean) equals mean.
sigma0
x0
+- 3*sigma0. See also options
scaling_of_variables
. Often one wants to check for
solutions close to the initial point. This allows,
for example, for an easier check of consistency of the
objective function and its interfacing with the optimizer.
In this case, a much smaller sigma0
is advisable.inopts
cma.CMAOptions
.self.incumbent
in inside the bounds.tentative copy of self, versatile (interface and functionalities may change).
This may not work depending on the used sampler.
Copy mean and sample distribution parameters and input options.
Do not copy evolution paths, termination status or other state variables.