~

AAAI2021/paper.tex

@@ -226,7 +226,8 @@
 \input{tex/experiments.tex}
 \input{tex/last.tex}
 
-
+\clearpage
+\newpage
 \bibliography{ref.bib}
 
 \end{document}

AAAI2021/tex/theory.tex

@@ -108,6 +108,7 @@ expected reward $ J(theta_S, theta_L)$ can be calculated as follows:
 \begin{algorithm}[t]
   \caption{Learning Algorithm$(t,\hat{t})$}
   \label{al:learning}
+  \small
 	\begin{algorithmic}[1]
 		\IF{Training the speaker agent S}
 		\FOR{Batch T randomly selected from $M_0\times M_1$}