libcmaesr: R Interface to 'libcmaes'

A lightweight interface to the 'libcmaes' C++ library for the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). CMA-ES is a state-of-the-art evolutionary algorithm for the optimization of difficult non-linear, non-convex black-box functions, as described in Hansen and Ostermeier (2001) <doi:10.1162/106365601750190398>. Supports the active, separable, and VD (diagonal plus rank-one covariance) variants of the algorithm as well as the IPOP (increasing population size) and BIPOP (bi-population) restart strategies. A patched copy of 'libcmaes' (LGPL >= 3) is bundled; see the COPYRIGHTS file for details.

Version:	0.1.0
Depends:	R (≥ 4.2.0)
Imports:	checkmate, mlr3misc, stats
LinkingTo:	RcppEigen
Suggests:	testthat (≥ 3.0.0), callr
Published:	2026-08-07
DOI:	10.32614/CRAN.package.libcmaesr (may not be active yet)
Author:	Marc Becker [aut, cre, cph], Bernd Bischl [aut], Martin Binder [aut], Lars Kotthoff [aut], Emmanuel Benazera [ctb, cph] (author of the bundled 'libcmaes' library), Inria [cph] (copyright holder of parts of the bundled 'libcmaes' library)
Maintainer:	Marc Becker <marcbecker at posteo.de>
BugReports:	https://github.com/mlr-org/libcmaesr/issues
License:	LGPL (≥ 3)
Copyright:	See the file COPYRIGHTS for details on the bundled 'libcmaes' copyrights libcmaesr copyright details
URL:	https://libcmaesr.mlr-org.com, https://github.com/mlr-org/libcmaesr
NeedsCompilation:	yes
Language:	en-US
Materials:	README, NEWS
CRAN checks:	libcmaesr results

Documentation:

Reference manual:

libcmaesr.html , libcmaesr.pdf

Downloads:

Package source:	libcmaesr_0.1.0.tar.gz
Windows binaries:	r-devel: not available, r-release: not available, r-oldrel: not available
macOS binaries:	r-release (arm64): libcmaesr_0.1.0.tgz, r-oldrel (arm64): libcmaesr_0.1.0.tgz, r-release (x86_64): libcmaesr_0.1.0.tgz, r-oldrel (x86_64): libcmaesr_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=libcmaesr to link to this page.