随机方差缩减的递归动量策略梯度方法
辛垚辉,李永强,冯宇,胡磊

Stochastic variance-reduced recursive momentum policy gradient method
Yaohui XIN,Yongqiang LI,Yu FENG,Lei HU
表 1 部分算法对寻找$ \epsilon $-稳定解的复杂度实例
Tab.1 Examples of complexity of partial algorithms for finding $ \epsilon - $stable solutions
方法VR技术样本复杂度小样本复杂度
GPOMDP[7]$ \mathcal{O}({\epsilon }^{-4}) $
SVRPG[18]SVRG[13]$ \mathcal{O}({\epsilon }^{-10/3}) $$ \mathcal{O}({\epsilon }^{-4/3}) $
STORM-PG[20]SARAH[14]$ \mathcal{O}({\epsilon }^{-3}) $$ \mathcal{O}(1) $
PAGE-PG[21]PAGE[17]$ \mathcal{O}({\epsilon }^{-3}) $$ \mathcal{O}(1) $
SVRRM-PGSVRRM[24]$ \mathcal{O}({\epsilon }^{-3}) $$ \mathcal{O}(1) $