×

Natural evolution strategies. (English) Zbl 1318.68159

Summary: 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.

MSC:

68T05 Learning and adaptive systems in artificial intelligence
90C59 Approximation methods and heuristics in mathematical programming
PDFBibTeX XMLCite
Full Text: Link