symbolically create MAML graph, for the meta-optimization, only called at the beginning of meta-training. Called more than once if you want t

Apply batch normalization to an existing layer. This is a convenience function modifying an existing layer to include batch normalization: It

abstract method, display some iteration infos if ``self.iteration_counter % modulo == 0``

Evaluates all option values in environment `loc`. :See: `eval()`

:type layer: Layer | list[Layer] :rtype: list[Layer]

returns a tuple (width, height)

Inject entry-wise noise to the observation. This should not change the dimension of the observation.

Runs Lanczos algorithm to generate a orthogonal basis for the Krylov subspace b, Ab, A^2b, ... as well as the upper hessenberg matrix T =

Taken from https://www.cs.hmc.edu/ACM/lectures/intersections.html this returns the intersection of Line(pt1,pt2) and Line(ptA,ptB) retu

plot data from files written by a `CMADataLogger`, the call ``cma.plot(name, **argsdict)`` is a shortcut for ``cma.CMADataLogger(name).pl

Ask a yes/no question via raw_input() and return their answer. "question" is a string that is presented to the user. "default" is the presume

``self.mean + self.random_rescaling_factor_to_mahalanobis_size(y)`` is guarantied to appear like from the sample distribution.

Check if the ray originated from (x, y) with direction theta intersects the line segment (x1, y1) -- (x2, y2), and return the intersection po

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

Run one timestep of the environment's dynamics. When end of episode is reached, reset() should be called to reset the environment's i

pass objective function values to prepare for next iteration. This core procedure of the CMA-ES algorithm updates all state variables,