..

AAAI2021/tex/theory.tex

@@ -6,7 +6,7 @@ including the environment setup, agent architecture, and training algorithm.
 
 
 \begin{figure}[t]
-  \centering  \includegraphics[width=0.99\columnwidth]{fig/Figure2_The_referential_game_environment.pdf}
+  \centering  \includegraphics[width=\columnwidth]{fig/Figure2_The_referential_game_environment.pdf}
   \caption{The referential game in this paper.}
   \label{fig:game}
 \end{figure}

AAAI2021/tex/theory2.tex

@@ -5,7 +5,7 @@ MIS is the similarity between an identity matrix and the mutual information matr
 
 \begin{figure}[t]
   \centering
-  \includegraphics[width=0.99\columnwidth]{fig/Figure4_The_information_channel.pdf}
+  \includegraphics[width=\columnwidth]{fig/Figure4_The_information_channel.pdf}
   \caption{The information channel modeling of the agents in the referential game.}
   \label{fig:modeling}
 \end{figure}
@@ -51,7 +51,7 @@ following formula:
 
 \begin{figure}[t]
   \centering
-  \includegraphics[width=0.9\columnwidth]{fig/Figure5_An_emergent_language.pdf}
+  \includegraphics[width=\columnwidth]{fig/Figure5_An_emergent_language.pdf}
   \caption{An emergent language that the unilateral metrics cannot measure its non-compositionality. Notice that when $s_1 = \mathrm{a}$, the listener can neither determine the shape nor the color without the knowledge about $s_0$.}
   \label{fig:unilateral}
 \end{figure}