Improving Evolutionary Strategies with Generative Neural Networks

Louis Faury, Clement Calauzenes, Olivier Fercoq, Syrine Krichen

Evolutionary Strategies (ES) are a popular family of black-box zeroth-order optimization algorithms which rely on search distributions to efficiently optimize a large variety of objective functions. This paper investigates the potential benefits of using highly flexible search distributions in classical ES algorithms, in contrast to standard ones (typically Gaussians). We model such distributions with Generative Neural Networks (GNNs) and introduce a new training algorithm that leverages their expressiveness to accelerate the ES procedure. We show that this tailored algorithm can readily incorporate existing ES algorithms, and outperforms the state-of-the-art on diverse objective functions.

Knowledge Graph

arrow_drop_up

Comments

Sign up or login to leave a comment