提交 34804c93 编写于 作者: X xiaowei_xing

test

上级 0325ddf7
......@@ -689,4 +689,14 @@ $$
\lVert\overline{G}\rVert_{1} = \lVert (I-\gamma P_{\pi'})^{-1} \rVert_{1} = \lVert \sum_{t=0}^{\infty}\gamma^{t} P_{\pi'}^{t} \rVert_{1} \leq \sum_{t=0}^{\infty} \gamma^{t} \lVert P
_ {\pi'} \rVert_{1}^{t} = \frac{1}{1-\gamma},
\tag{14}
$$
接下来限制 $\lVert \Delta d^{\pi} \rVert_{1}$。
$$
\lVert \Delta d^{\pi} \rVert_{1} = \sum_{s'} |\sum_{s} \Delta(s'|s)d^{\pi}(s)|
$$
$$
\leq \sum_{s',s}|\Delta(s'|s)|d^{\pi}(s)
$$
\ No newline at end of file
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册