论文标题

进化策略会汇合到有限的差异

Evolution Strategies Converges to Finite Differences

论文作者

Raisbeck, John C., Allen, Matthew, Weissleder, Ralph, Im, Hyungsoon, Lee, Hakho

论文摘要

自从Salimans等人的演化策略(ES)作为增强学习的工具以来。 2017年,人们一直有兴趣确定进化策略梯度与类似算法的梯度之间的确切关系,有限的差异(FD)(Zhang等人,2017年,Lehman等人,Lehman等人,2018年)对受试者进行了几项调查,对受试者进行了几项调查,并研究了正式的动机差异(Lehman等人之间的差异(Lehman等人),以及在ES和FD之间进行了差异,以及ES和FD的差异,以及一个差异,以及在ES和FD之间进行了差异。 MNIST分类问题(Zhang等,2017)。本文证明,尽管梯度不同,但随着优化矢量的尺寸增加,它们会融合。

Since the debut of Evolution Strategies (ES) as a tool for Reinforcement Learning by Salimans et al. 2017, there has been interest in determining the exact relationship between the Evolution Strategies gradient and the gradient of a similar class of algorithms, Finite Differences (FD).(Zhang et al. 2017, Lehman et al. 2018) Several investigations into the subject have been performed, investigating the formal motivational differences(Lehman et al. 2018) between ES and FD, as well as the differences in a standard benchmark problem in Machine Learning, the MNIST classification problem(Zhang et al. 2017). This paper proves that while the gradients are different, they converge as the dimension of the vector under optimization increases.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源