RL-赵-(六):随机逼近与随机梯度下降02-2:Robbins-Monro(RM)算法【wₖ₊₁=wₖ-αₖĝ(wₖ,ηₖ)】【SA领域的开创性工作】
2、Robbins-Monro(RM)算法
Robbins-Monro(RM)算法: wk+1 = wk − ak g~(wk,ηk ),k = 1,2,3,... \begin{aligned}w_{k+1}\:=\:w_k\:-\:a_k\:\tilde{g}(w_k,\eta_k\:),k\:=\:1,2,3,...\end{aligned} wk+1=wk−akg~(wk,ηk),k=1,2,3,...
其中 wkw_kwk…
2026/9/24 6:47:21