~

AAAI2021/tex/experiments.tex

 \section{Experiments}
 \label{sec:exp}
+
+\subsection{}
+\label{ssec:}
+
+We examine the compositionality of symbolic language that emerged in our natural
+referential game with various vocabulary size. For each configuration of
+vocabulary size, we train the speaker-listener agents to emerge symbolic
+language under different agent capacities, i.e., hidden layer size ($h_{size}$).
+
+\begin{figure}[t]
+  \centering
+  \includegraphics[width=0.9\columnwidth]{fig/occupy}
+  \caption{Compositionality of symbolic language under different parameters.}
+  \label{fig:exp1}
+\end{figure}
+
+
+
+\subsection{}
+\label{ssec:}
+