CMA-HAGA is a state-of-the-art algorithm for complex real-world optimisation problems. It has been developed over five years, and applied to problems from fields including mechanical engineering, physics, control theory, and health.
As part of the Computational Intelligence Research Initiative (CIRI), an up-to-date CMA-HAGA implementation has now been publicly released. This implementation has been written in Python and will allow anyone to take advantage of the algorithm’s performance.
Relevant recent publications for the interested reader:
- Covariance matrix adaptation pareto archived evolution strategy with hypervolume-sorted adaptive grid algorithm
- A fast hypervolume driven selection mechanism for many-objective optimisation problems
Introductory videos:
