Merge branch 'master' of http://62.234.201.16/hao/AAAI21_Emergent_language

“haoyifan”

AAAI2021/tex/Experimental Framework.tex

@@ -51,7 +51,7 @@ Unlike previous studies[][], the agents in this paper are totally independent. I
 		\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 $\pi_{old}^L\leftarrow \pi^L$