Previous works focus on the \emph{deliberately handcrafted} inductions that affect the
compositionality of emergent language.
Some significant works on studying the environmental inductions on the compositionality of emergent language are summarized in Table~\ref{tab:rel}.
For example, ~\cite{kirby2015compression} explored how the pressures for expressivity and compressibility lead the structured language.
For example,
~\cite{gupta2020compositionality} used a structural dependent agents, i.e., a variational autoencoder, to simulate a speaker-listener pair, and constrained the communication channel into a binary coding sequence.
~\cite{kirby2015compression} explored how the pressures for expressivity and compressibility lead the structured language.
~\cite{kottur-etal-2017-natural} constrained the vocabulary size and whether the listener has memory to coax the compositionality of the emergent language.
~\cite{lazaridou2018emergence} showed that the degree of structure found in the input data affects the emergence of the symbolic language.
~\cite{li2019ease} studied how the pressure, ease of teaching, impact on the iterative language of the population regime.
~\cite{li2019ease} studied how the \emph{ease of teaching} pressure, created by resetting listener repeatly when training agents, impact on the iterative language of the population regime.
~\cite{evtimova2018emergent} designed novel multi-modal scenarios, which the speaker and the listener should access to different modalities of the input object, to explore the language emergence.
These inductions are deliberately designed, which are too ideal to be true in
