\section{Async\+Learning$<$ Worker\+Type, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$ Class Template Reference} \label{classmlpack_1_1rl_1_1AsyncLearning}\index{Async\+Learning$<$ Worker\+Type, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$@{Async\+Learning$<$ Worker\+Type, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$}} Wrapper of various asynchronous learning algorithms, e.\+g. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Async\+Learning} (\textbf{ Training\+Config} config, Network\+Type network, Policy\+Type policy, Updater\+Type updater=Updater\+Type(), Environment\+Type environment=Environment\+Type()) \begin{DoxyCompactList}\small\item\em Construct an instance of the given async learning algorithm. \end{DoxyCompactList}\item \textbf{ Training\+Config} \& \textbf{ Config} () \begin{DoxyCompactList}\small\item\em Get training config. \end{DoxyCompactList}\item const \textbf{ Training\+Config} \& \textbf{ Config} () const \begin{DoxyCompactList}\small\item\em Modify training config. \end{DoxyCompactList}\item Environment\+Type \& \textbf{ Environment} () \begin{DoxyCompactList}\small\item\em Get the environment. \end{DoxyCompactList}\item const Environment\+Type \& \textbf{ Environment} () const \begin{DoxyCompactList}\small\item\em Modify the environment. \end{DoxyCompactList}\item Network\+Type \& \textbf{ Network} () \begin{DoxyCompactList}\small\item\em Get learning network. \end{DoxyCompactList}\item const Network\+Type \& \textbf{ Network} () const \begin{DoxyCompactList}\small\item\em Modify learning network. \end{DoxyCompactList}\item Policy\+Type \& \textbf{ Policy} () \begin{DoxyCompactList}\small\item\em Get behavior policy. \end{DoxyCompactList}\item const Policy\+Type \& \textbf{ Policy} () const \begin{DoxyCompactList}\small\item\em Modify behavior policy. \end{DoxyCompactList}\item {\footnotesize template$<$typename Measure $>$ }\\void \textbf{ Train} (Measure \&measure) \begin{DoxyCompactList}\small\item\em Starting async training. \end{DoxyCompactList}\item Updater\+Type \& \textbf{ Updater} () \begin{DoxyCompactList}\small\item\em Get optimizer. \end{DoxyCompactList}\item const Updater\+Type \& \textbf{ Updater} () const \begin{DoxyCompactList}\small\item\em Modify optimizer. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Worker\+Type, typename Environment\+Type, typename Network\+Type, typename Updater\+Type, typename Policy\+Type$>$\newline class mlpack\+::rl\+::\+Async\+Learning$<$ Worker\+Type, Environment\+Type, Network\+Type, Updater\+Type, Policy\+Type $>$} Wrapper of various asynchronous learning algorithms, e.\+g. async one-\/step Q-\/learning, async one-\/step Sarsa, async n-\/step Q-\/learning and async advantage actor-\/critic. For more details, see the following\+: \begin{DoxyCode} @inproceedings\{mnih2016asynchronous, title = \{Asynchronous methods \textcolor{keywordflow}{for} deep reinforcement learning\}, author = \{Mnih, Volodymyr and Badia, Adria Puigdomenech and Mirza, Mehdi and Graves, Alex and Lillicrap, Timothy and Harley, Tim and Silver, David and Kavukcuoglu, Koray\}, booktitle = \{International Conference on Machine Learning\}, pages = \{1928--1937\}, year = \{2016\} \} \end{DoxyCode} \begin{DoxyTemplParams}{Template Parameters} {\em Worker\+Type} & The type of the worker. \\ \hline {\em Environment\+Type} & The type of 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 57 of file async\+\_\+learning.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_a107901cf3bb6acfdc35a11eb8721def9}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Async\+Learning@{Async\+Learning}} \index{Async\+Learning@{Async\+Learning}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Async\+Learning()} {\footnotesize\ttfamily \textbf{ Async\+Learning} (\begin{DoxyParamCaption}\item[{\textbf{ Training\+Config}}]{config, }\item[{Network\+Type}]{network, }\item[{Policy\+Type}]{policy, }\item[{Updater\+Type}]{updater = {\ttfamily UpdaterType()}, }\item[{Environment\+Type}]{environment = {\ttfamily EnvironmentType()} }\end{DoxyParamCaption})} Construct an instance of the given async learning algorithm. \begin{DoxyParams}{Parameters} {\em config} & Hyper-\/parameters for training. \\ \hline {\em network} & The network model. \\ \hline {\em policy} & The behavior policy. \\ \hline {\em updater} & The optimizer. \\ \hline {\em environment} & The reinforcement learning task. \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_a9428142f6a4c6d03657200fde2dda9c9}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Config@{Config}} \index{Config@{Config}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Config()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily \textbf{ Training\+Config}\& Config (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Get training config. Definition at line 92 of file async\+\_\+learning.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_a10bc8bd4dab7fba79b770fdd1bb63a8f}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Config@{Config}} \index{Config@{Config}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Config()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily const \textbf{ Training\+Config}\& Config (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Modify training config. Definition at line 94 of file async\+\_\+learning.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_a59cc43eb892c46ea7c50e18fb78b9172}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Environment@{Environment}} \index{Environment@{Environment}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Environment()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Environment\+Type\& Environment (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Get the environment. Definition at line 112 of file async\+\_\+learning.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_adc517fd7b152925b4297e09a3bb4afe0}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Environment@{Environment}} \index{Environment@{Environment}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Environment()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily const Environment\+Type\& Environment (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Modify the environment. Definition at line 114 of file async\+\_\+learning.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_a3802bdee893a3f86fb9fa08cbbc8239c}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Network@{Network}} \index{Network@{Network}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Network()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Network\+Type\& Network (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Get learning network. Definition at line 97 of file async\+\_\+learning.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_a0ce8c122193c6a20fd4b397bc8525f7d}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Network@{Network}} \index{Network@{Network}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Network()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily const Network\+Type\& Network (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Modify learning network. Definition at line 99 of file async\+\_\+learning.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_a1ef80c7b0a3fb5468b9d920fef109d36}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Policy@{Policy}} \index{Policy@{Policy}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Policy()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Policy\+Type\& Policy (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Get behavior policy. Definition at line 102 of file async\+\_\+learning.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_a04e9dd2c0ef71ea0e2cb126233652bfa}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Policy@{Policy}} \index{Policy@{Policy}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Policy()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily const Policy\+Type\& Policy (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Modify behavior policy. Definition at line 104 of file async\+\_\+learning.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_ae1533b4fc586f67a0c38757ed08a27c7}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Train@{Train}} \index{Train@{Train}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Train()} {\footnotesize\ttfamily void Train (\begin{DoxyParamCaption}\item[{Measure \&}]{measure }\end{DoxyParamCaption})} Starting async training. \begin{DoxyTemplParams}{Template Parameters} {\em Measure} & The type of the measurement. It should be a callable object like \begin{DoxyCode} \textcolor{keywordtype}{bool} foo(\textcolor{keywordtype}{double} reward); \end{DoxyCode} where reward is the total reward of a deterministic test episode, and the return value should indicate whether the training process is completed. \\ \hline \end{DoxyTemplParams} \begin{DoxyParams}{Parameters} {\em measure} & The measurement instance. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_abbd240500a77c5f76a69eb874862d4ec}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Updater@{Updater}} \index{Updater@{Updater}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Updater()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Updater\+Type\& Updater (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Get optimizer. Definition at line 107 of file async\+\_\+learning.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1AsyncLearning_af345bba27115c3d09fa7b06fc1c984a4}} \index{mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}!Updater@{Updater}} \index{Updater@{Updater}!mlpack\+::rl\+::\+Async\+Learning@{mlpack\+::rl\+::\+Async\+Learning}} \subsubsection{Updater()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily const Updater\+Type\& Updater (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Modify optimizer. Definition at line 109 of file async\+\_\+learning.\+hpp. The documentation for this class was generated from the following file\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/git/src/mlpack/methods/reinforcement\+\_\+learning/\textbf{ async\+\_\+learning.\+hpp}\end{DoxyCompactItemize}