Publication
Natural evolution strategies
Daan Wierstra; Tom Schaul; Tobias Glasmachers; Yi Sun; Jan Peters; Jürgen Schmidhuber
In: Journal of Machine Learning Research, Vol. 15, No. 1, Pages 949-980, JMLR, 2014.
Abstract
This paper presents Natural Evolution Strategies (NES), a recent family of black-box optimization algorithms that use the natural gradient to update a parameterized search distribution in the direction of higher expected fitness. We introduce a collection of techniques that address issues of convergence, robustness, sample complexity, computational complexity and sensitivity to hyperparameters. This paper explores a number of implementations of the NES family, such as general-purpose multi-variate normal distributions and separable distributions tailored towards search in high dimensional spaces. Experimental results show best published performance on various standard benchmarks, as well as competitive performance on others.