Commit 4993b75a by Zidong Du

~

parent 8792085f
......@@ -226,7 +226,8 @@
\input{tex/experiments.tex}
\input{tex/last.tex}
\clearpage
\newpage
\bibliography{ref.bib}
\end{document}
......@@ -108,6 +108,7 @@ expected reward $ J(theta_S, theta_L)$ can be calculated as follows:
\begin{algorithm}[t]
\caption{Learning Algorithm$(t,\hat{t})$}
\label{al:learning}
\small
\begin{algorithmic}[1]
\IF{Training the speaker agent S}
\FOR{Batch T randomly selected from $M_0\times M_1$}
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment