updates
This commit is contained in:
12
result.tex
12
result.tex
@@ -214,11 +214,13 @@ What is not used:
|
||||
\newpage
|
||||
\item [2.4] Bonus (20pt)
|
||||
|
||||
% \begin{figure}[H]
|
||||
% \centering
|
||||
% \includegraphics[width=0.8\textwidth]{images/p241.png}
|
||||
% \caption{Learning Curve for Average Return for HalfCheetah with Berkely Parameters}
|
||||
% \end{figure}
|
||||
\begin{figure}[H]
|
||||
\centering
|
||||
\includegraphics[width=0.8\textwidth]{images/p24.png}
|
||||
\caption{Learning Curve for Average Return for HalfCheetah with Berkely Parameters}
|
||||
\end{figure}
|
||||
|
||||
Unfortunately, the experiments with Berkely parameters do not converge to the maximum reward of 300. We tested different batch sizes and learning rates, but the results are still not satisfactory. Even with increasing epoch, the performance is still not beyond random movement.
|
||||
|
||||
\end{enumerate}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user