@@ -72,13 +72,13 @@ vocabulary can express almost infinite concepts.}
\end{table*}
Prior studies focus on achieving high compositional symbolic language
through \emph{deliberately handcrafted} inductions, e.g., additional rewards~\cite{},
through \emph{deliberately handcrafted} inductions, e.g., additional rewards~\cite{mordatch2017emergence},
constructed loss functions~\cite{kharitonov2019egg}, structural input data~\cite{lazaridou2018emergence,evtimova2018emergent},
memoryless~\cite{kottur-etal-2017-natural,li2019ease}, and ease-of-teaching~\cite{li2019ease}.
\note{Such optimization methodologies are driven by the challenges to generate high compositional symbolic without induction in an existing multi-agent environment.}
Figure~\ref{fig:induction} reports the compositionality when training two agents
in the widely-used listener-speaker referential game~\cite{} for emerging 100
in the widely-used listener-speaker referential game~\cite{david1969convention} for emerging 100
languages, and it can be observed that \note{the compositionality
of emergent language is seldom high (e.g., $<5\%$ for compositionality $>0.99$)
