Update theory.tex

AAAI2021/tex/theory.tex

@@ -45,7 +45,7 @@
 		\STATE $P(\hat{t}|s) = \pi^L_{old}(\hat{t}|s)$ 
 		\STATE Sample $\hat{t}$ with $P(\hat{t}|s)$
 		\STATE Get reward $r(\hat{t},t)$
-		\STATE $J(\theta^S,\theta^L)=E_{\pi_{old}^S,\pi^L}[r(\hat{t},t)\cdot\frac{\pi^L(s|t)}{\pi^L_{old}(s|t)}]$
+		\STATE $J(\theta^S,\theta^L)=E_{\pi^S,\pi_{old}^L}[r(\hat{t},t)\cdot\frac{\pi^L(s|t)}{\pi^L_{old}(s|t)}]$
 		\STATE Update $\theta^L$ by $\bigtriangledown_{\theta^L}J$
 		\ENDFOR
 		\STATE $\pi_{old}^L\leftarrow \pi^L$