This paper presents Natural Evolution Strategies (NES), a recent family of
algorithms that constitute a more principled approach to black-box optimization
than established evolutionary algorithms. NES maintains a parameterized
distribution on the set of solution candidates, and the natural gradient is
used to update the distribution's parameters 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, ranging from general-purpose multi-variate normal
distributions to heavy-tailed and separable distributions tailored towards
global optimization and search in high dimensional spaces, respectively.
Experimental results show best published performance on various standard
benchmarks, as well as competitive performance on others.

本文提出了一种名为自然进化策略（NES）的算法，它是一种比传统进化算法更为规范的黑盒优化方法。NES 在候选解集上维护一个参数化的分布，使用自然梯度来更新分布的参数，以求解更高预期的适应度值。本文介绍了一系列技术，解决了关于收敛、稳健性、样本复杂度、计算复杂度和对超参数的敏感性等问题。对于全局优化和高维空间搜索，从通用的多元正态分布到重尾和可分布的分布，本文探讨了 NES 系列的多种实现。实验结果显示，NES 表现良好，达到了各种标准基准测试的最佳性能。