Jelajahi Sumber

代修订16.8

Sm1les 6 tahun lalu
induk
melakukan
3e02330e06
1 mengubah file dengan 1 tambahan dan 1 penghapusan
  1. 1 1
      docs/chapter16/chapter16.md

+ 1 - 1
docs/chapter16/chapter16.md

@@ -71,7 +71,7 @@ $$
 V_{\gamma }^{\pi}(x)&=\mathbb{E}_{\pi}[\sum_{t=0}^{\infty }\gamma^{t}r_{t+1}\mid x_{0}=x]\\
 &=\mathbb{E}_{\pi}[r_{1}+\sum_{t=1}^{\infty}\gamma^{t}r_{t+1}\mid x_{0}=x]\\
 &=\mathbb{E}_{\pi}[r_{1}+\gamma\sum_{t=1}^{\infty}\gamma^{t-1}r_{t+1}\mid x_{0}=x]\\
-&=\sum _{a\in A}\pi(x,a)\sum_{x{}'\in X}P_{x\rightarrow x{}'}^{a}(R_{x\rightarrow x{}'}^{a}+\gamma \mathbb{E}_{\pi}[\sum_{t=1}^{\infty }\gamma^{t}r_{t+1}\mid x_{0}=x{}'])\\
+&=\sum _{a\in A}\pi(x,a)\sum_{x{}'\in X}P_{x\rightarrow x{}'}^{a}(R_{x\rightarrow x{}'}^{a}+\gamma \mathbb{E}_{\pi}[\sum_{t=0}^{\infty }\gamma^{t}r_{t+1}\mid x_{0}=x{}'])\\
 &=\sum _{a\in A}\pi(x,a)\sum_{x{}'\in X}P_{x\rightarrow x{}'}^{a}(R_{x\rightarrow x{}'}^{a}+\gamma V_{\gamma }^{\pi}(x{}'))
 \end{aligned}
 $$