\section{mlpack\+:\+:rl Namespace Reference}
\label{namespacemlpack_1_1rl}\index{mlpack\+::rl@{mlpack\+::rl}}
\subsection*{Classes}
\begin{DoxyCompactItemize}
\item 
class \textbf{ Acrobot}
\begin{DoxyCompactList}\small\item\em Implementation of \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} game. \end{DoxyCompactList}\item 
class \textbf{ Aggregated\+Policy}
\item 
class \textbf{ Async\+Learning}
\begin{DoxyCompactList}\small\item\em Wrapper of various asynchronous learning algorithms, e.\+g. \end{DoxyCompactList}\item 
class \textbf{ Cart\+Pole}
\begin{DoxyCompactList}\small\item\em Implementation of Cart Pole task. \end{DoxyCompactList}\item 
class \textbf{ Continuous\+Double\+Pole\+Cart}
\begin{DoxyCompactList}\small\item\em Implementation of Continuous Double Pole Cart Balancing task. \end{DoxyCompactList}\item 
class \textbf{ Continuous\+Mountain\+Car}
\begin{DoxyCompactList}\small\item\em Implementation of Continuous Mountain Car task. \end{DoxyCompactList}\item 
class \textbf{ Double\+Pole\+Cart}
\begin{DoxyCompactList}\small\item\em Implementation of Double Pole Cart Balancing task. \end{DoxyCompactList}\item 
class \textbf{ Greedy\+Policy}
\begin{DoxyCompactList}\small\item\em Implementation for epsilon greedy policy. \end{DoxyCompactList}\item 
class \textbf{ Mountain\+Car}
\begin{DoxyCompactList}\small\item\em Implementation of Mountain Car task. \end{DoxyCompactList}\item 
class \textbf{ N\+Step\+Q\+Learning\+Worker}
\begin{DoxyCompactList}\small\item\em Forward declaration of \doxyref{N\+Step\+Q\+Learning\+Worker}{p.}{classmlpack_1_1rl_1_1NStepQLearningWorker}. \end{DoxyCompactList}\item 
class \textbf{ One\+Step\+Q\+Learning\+Worker}
\begin{DoxyCompactList}\small\item\em Forward declaration of \doxyref{One\+Step\+Q\+Learning\+Worker}{p.}{classmlpack_1_1rl_1_1OneStepQLearningWorker}. \end{DoxyCompactList}\item 
class \textbf{ One\+Step\+Sarsa\+Worker}
\begin{DoxyCompactList}\small\item\em Forward declaration of \doxyref{One\+Step\+Sarsa\+Worker}{p.}{classmlpack_1_1rl_1_1OneStepSarsaWorker}. \end{DoxyCompactList}\item 
class \textbf{ Pendulum}
\begin{DoxyCompactList}\small\item\em Implementation of \doxyref{Pendulum}{p.}{classmlpack_1_1rl_1_1Pendulum} task. \end{DoxyCompactList}\item 
class \textbf{ Prioritized\+Replay}
\begin{DoxyCompactList}\small\item\em Implementation of prioritized experience replay. \end{DoxyCompactList}\item 
class \textbf{ Q\+Learning}
\begin{DoxyCompactList}\small\item\em Implementation of various Q-\/\+Learning algorithms, such as D\+QN, double D\+QN. \end{DoxyCompactList}\item 
class \textbf{ Random\+Replay}
\begin{DoxyCompactList}\small\item\em Implementation of random experience replay. \end{DoxyCompactList}\item 
class \textbf{ Reward\+Clipping}
\begin{DoxyCompactList}\small\item\em Interface for clipping the reward to some value between the specified maximum and minimum value (Clipping here is implemented as $ g_{\text{clipped}} = \max(g_{\text{min}}, \min(g_{\text{min}}, g))) $.) \end{DoxyCompactList}\item 
class \textbf{ Sum\+Tree}
\begin{DoxyCompactList}\small\item\em Implementation of \doxyref{Sum\+Tree}{p.}{classmlpack_1_1rl_1_1SumTree}. \end{DoxyCompactList}\item 
class \textbf{ Training\+Config}
\end{DoxyCompactItemize}
\subsection*{Typedefs}
\begin{DoxyCompactItemize}
\item 
{\footnotesize template$<$typename Environment\+Type , typename Network\+Type , typename Updater\+Type , typename Policy\+Type $>$ }\\using \textbf{ N\+Step\+Q\+Learning} = \textbf{ Async\+Learning}$<$ \textbf{ N\+Step\+Q\+Learning\+Worker}$<$ Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$
\begin{DoxyCompactList}\small\item\em Convenient typedef for async n step q-\/learning. \end{DoxyCompactList}\item 
{\footnotesize template$<$typename Environment\+Type , typename Network\+Type , typename Updater\+Type , typename Policy\+Type $>$ }\\using \textbf{ One\+Step\+Q\+Learning} = \textbf{ Async\+Learning}$<$ \textbf{ One\+Step\+Q\+Learning\+Worker}$<$ Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$
\begin{DoxyCompactList}\small\item\em Convenient typedef for async one step q-\/learning. \end{DoxyCompactList}\item 
{\footnotesize template$<$typename Environment\+Type , typename Network\+Type , typename Updater\+Type , typename Policy\+Type $>$ }\\using \textbf{ One\+Step\+Sarsa} = \textbf{ Async\+Learning}$<$ \textbf{ One\+Step\+Sarsa\+Worker}$<$ Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$
\begin{DoxyCompactList}\small\item\em Convenient typedef for async one step Sarsa. \end{DoxyCompactList}\end{DoxyCompactItemize}


\subsection{Typedef Documentation}
\mbox{\label{namespacemlpack_1_1rl_a5af8bcbe29f6b50332ea2ac7d7dd521b}} 
\index{mlpack\+::rl@{mlpack\+::rl}!N\+Step\+Q\+Learning@{N\+Step\+Q\+Learning}}
\index{N\+Step\+Q\+Learning@{N\+Step\+Q\+Learning}!mlpack\+::rl@{mlpack\+::rl}}
\subsubsection{N\+Step\+Q\+Learning}
{\footnotesize\ttfamily using \textbf{ N\+Step\+Q\+Learning} =  \textbf{ Async\+Learning}$<$\textbf{ N\+Step\+Q\+Learning\+Worker}$<$Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type$>$, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type$>$}



Convenient typedef for async n step q-\/learning. 


\begin{DoxyTemplParams}{Template Parameters}
{\em Environment\+Type} & The type of the reinforcement learning task. \\
\hline
{\em Network\+Type} & The type of the network model. \\
\hline
{\em Updater\+Type} & The type of the optimizer. \\
\hline
{\em Policy\+Type} & The type of the behavior policy. \\
\hline
\end{DoxyTemplParams}


Definition at line 233 of file async\+\_\+learning.\+hpp.

\mbox{\label{namespacemlpack_1_1rl_a3c2fb6897a13583e67422ad12286f6d1}} 
\index{mlpack\+::rl@{mlpack\+::rl}!One\+Step\+Q\+Learning@{One\+Step\+Q\+Learning}}
\index{One\+Step\+Q\+Learning@{One\+Step\+Q\+Learning}!mlpack\+::rl@{mlpack\+::rl}}
\subsubsection{One\+Step\+Q\+Learning}
{\footnotesize\ttfamily using \textbf{ One\+Step\+Q\+Learning} =  \textbf{ Async\+Learning}$<$\textbf{ One\+Step\+Q\+Learning\+Worker}$<$Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type$>$, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type$>$}



Convenient typedef for async one step q-\/learning. 


\begin{DoxyTemplParams}{Template Parameters}
{\em Environment\+Type} & The type of the reinforcement learning task. \\
\hline
{\em Network\+Type} & The type of the network model. \\
\hline
{\em Updater\+Type} & The type of the optimizer. \\
\hline
{\em Policy\+Type} & The type of the behavior policy. \\
\hline
\end{DoxyTemplParams}


Definition at line 197 of file async\+\_\+learning.\+hpp.

\mbox{\label{namespacemlpack_1_1rl_ae44ae2a1270ac28a3d57dd93439839a4}} 
\index{mlpack\+::rl@{mlpack\+::rl}!One\+Step\+Sarsa@{One\+Step\+Sarsa}}
\index{One\+Step\+Sarsa@{One\+Step\+Sarsa}!mlpack\+::rl@{mlpack\+::rl}}
\subsubsection{One\+Step\+Sarsa}
{\footnotesize\ttfamily using \textbf{ One\+Step\+Sarsa} =  \textbf{ Async\+Learning}$<$\textbf{ One\+Step\+Sarsa\+Worker}$<$Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type$>$, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type$>$}



Convenient typedef for async one step Sarsa. 


\begin{DoxyTemplParams}{Template Parameters}
{\em Environment\+Type} & The type of the reinforcement learning task. \\
\hline
{\em Network\+Type} & The type of the network model. \\
\hline
{\em Updater\+Type} & The type of the optimizer. \\
\hline
{\em Policy\+Type} & The type of the behavior policy. \\
\hline
\end{DoxyTemplParams}


Definition at line 215 of file async\+\_\+learning.\+hpp.