~

NIPS2020/main.tex

@@ -145,10 +145,35 @@ and the emergence of intelligence in individual human.
 %Symbolic Language is important
 
 
-% 
+%Recent effort for emergence is not correct
 
 
-\section{Symbolic Language}
+%In this paper, we proposed a SIC model
+
+
+%Our contribution
+
+
+\section{Background and Motivation}
+In this section, we introduce the \emph{Symbolic Language} and the major efforts
+related to the emergence symbolic language.
+
+\subsection{Symbolic Language}
+
+\subsection{Multi-agent Systems}
+Recent works are focusing on the emergence of grounded symbolic language in
+neuron network based multi-agent systems. The grounded symbolic language, where
+each symbol is mapped to its own meaning, is obtained by training the agents in
+systems. However, even using the multi-agent systems, previous works at root are
+training one brain for communicating among connected sensors (agents), as they combine
+the neural networks of all agents in the training process.
+
+Roughly, previous works force the agents evolving for generating communication
+protocol by setting a target that requires the cooperation of multiple
+agents. These works can be classified into two categories based on the
+environment settings: \emph{referential games} and \emph{multi-agent
+  reinforcement learning system}. 
+
 
 \section{The Self-grounding-Introspection-Cooperation Model}