-
Modular CMA is packaged and should be easy to integrate in Nevergrad.
Example of usage of "modcma" below:
import random
import numpy as np
from modcma import AskTellCMAES
DIMENSION = 10
…
-
Hi,
Great work on the toolkit!
I encountered a problem while employing the CMA-ES algorithm. Specifically, one parameter had a standard deviation of approximately `1e-6`, resulting in a varianc…
-
Leider funktioniert der Serienrecorder bei mir nicht. Ich habe einige Serienma…
-
https://github.com/CMA-ES/libcmaes/blob/bf994354c072e58f3125014a40029ee65cd7e00d/src/bipopcmastrategy.cc#L122
Should not the value sampled from uniform distribution be squared as suggested in:
htt…
-
## 論文情報
https://ipsjcva.springeropen.com/track/pdf/10.1186/s41074-017-0030-7?site=ipsjcva.springeropen.com
Yoshihiko Ozaki, Masaki Yano, and Masaki Onishi
## 一言で言うと
ネルダーミート法を用いたハイパーパラメータ最適化により、年…
-
I would like to evaluate all the candidate solutions at once (e.g., in order to coevolve them). Is that possible with the Python API?
-
Pymoo has a requirement of cma==3.2.2.
Is there any reason to fix the version, rather than using cma>=3.2.2 as is usually expected from a library? Is pymoo not compatible with cma 3.3.0?
This leads…
-
I have seen the libcmaes, which is a good contribution. I am wondering if this library can be applied for real application.
For example the task of modeling a 3D model, based on genetic algorithm to …
-
Being able to define constraints and doing parallelization over many processes would be very useful. As I understand it, right now only `fmin_con` allows for constrained optimisation but not parallel…
enajx updated
2 years ago
-
Hi, I have a bi-level problem where the lower level is solved by CPLEX and I would like to solve the upper level using CMA-ES. As shown in the examples, wee need to define a fitness function
`foo = …