\section{Reward\+Clipping$<$ Environment\+Type $>$ Class Template Reference} \label{classmlpack_1_1rl_1_1RewardClipping}\index{Reward\+Clipping$<$ Environment\+Type $>$@{Reward\+Clipping$<$ Environment\+Type $>$}} 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))) $.) \subsection*{Public Types} \begin{DoxyCompactItemize} \item using \textbf{ Action} = typename Environment\+Type\+::\+Action \begin{DoxyCompactList}\small\item\em Convenient typedef for action. \end{DoxyCompactList}\item using \textbf{ State} = typename Environment\+Type\+::\+State \begin{DoxyCompactList}\small\item\em Convenient typedef for state. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Reward\+Clipping} (Environment\+Type \&environment, const double min\+Reward=-\/1.\+0, const double max\+Reward=1.\+0) \begin{DoxyCompactList}\small\item\em Constructor for creating a \doxyref{Reward\+Clipping}{p.}{classmlpack_1_1rl_1_1RewardClipping} instance. \end{DoxyCompactList}\item Environment\+Type \& \textbf{ Environment} () const \begin{DoxyCompactList}\small\item\em Get the environment. \end{DoxyCompactList}\item Environment\+Type \& \textbf{ Environment} () \begin{DoxyCompactList}\small\item\em Modify the environment. \end{DoxyCompactList}\item \textbf{ State} \textbf{ Initial\+Sample} () \begin{DoxyCompactList}\small\item\em The Initial\+Sample method is called by the environment to initialize the starting state. \end{DoxyCompactList}\item bool \textbf{ Is\+Terminal} (const \textbf{ State} \&state) const \begin{DoxyCompactList}\small\item\em Checks whether given state is a terminal state. \end{DoxyCompactList}\item double \textbf{ Max\+Reward} () const \begin{DoxyCompactList}\small\item\em Get the maximum reward value. \end{DoxyCompactList}\item double \& \textbf{ Max\+Reward} () \begin{DoxyCompactList}\small\item\em Modify the maximum reward value. \end{DoxyCompactList}\item double \textbf{ Min\+Reward} () const \begin{DoxyCompactList}\small\item\em Get the minimum reward value. \end{DoxyCompactList}\item double \& \textbf{ Min\+Reward} () \begin{DoxyCompactList}\small\item\em Modify the minimum reward value. \end{DoxyCompactList}\item double \textbf{ Sample} (const \textbf{ State} \&state, const \textbf{ Action} \&action, \textbf{ State} \&next\+State) \begin{DoxyCompactList}\small\item\em Dynamics of Environment. \end{DoxyCompactList}\item double \textbf{ Sample} (const \textbf{ State} \&state, const \textbf{ Action} \&action) \begin{DoxyCompactList}\small\item\em Dynamics of Environment. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Environment\+Type$>$\newline class mlpack\+::rl\+::\+Reward\+Clipping$<$ Environment\+Type $>$} 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))) $.) \begin{DoxyTemplParams}{Template Parameters} {\em Environment\+Type} & A type of Environment that is being wrapped. \\ \hline \end{DoxyTemplParams} Definition at line 30 of file reward\+\_\+clipping.\+hpp. \subsection{Member Typedef Documentation} \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a1f2d996cd451bb1fed4d3d89b4ba19ba}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Action@{Action}} \index{Action@{Action}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Action} {\footnotesize\ttfamily using \textbf{ Action} = typename Environment\+Type\+::\+Action} Convenient typedef for action. Definition at line 37 of file reward\+\_\+clipping.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a1f6c591e4da193973060b0a606af688d}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!State@{State}} \index{State@{State}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{State} {\footnotesize\ttfamily using \textbf{ State} = typename Environment\+Type\+::\+State} Convenient typedef for state. Definition at line 34 of file reward\+\_\+clipping.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a97f34a1179082c279260959eff023e1f}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Reward\+Clipping@{Reward\+Clipping}} \index{Reward\+Clipping@{Reward\+Clipping}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Reward\+Clipping()} {\footnotesize\ttfamily \textbf{ Reward\+Clipping} (\begin{DoxyParamCaption}\item[{Environment\+Type \&}]{environment, }\item[{const double}]{min\+Reward = {\ttfamily -\/1.0}, }\item[{const double}]{max\+Reward = {\ttfamily 1.0} }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Constructor for creating a \doxyref{Reward\+Clipping}{p.}{classmlpack_1_1rl_1_1RewardClipping} instance. \begin{DoxyParams}{Parameters} {\em min\+Reward} & Minimum possible value of clipped reward. \\ \hline {\em max\+Reward} & Maximum possible value of clipped reward. \\ \hline {\em environment} & An instance of the environment used for actual simulations. \\ \hline \end{DoxyParams} Definition at line 47 of file reward\+\_\+clipping.\+hpp. \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a18f14a98092c29dd41d3e1cbc2c52159}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Environment@{Environment}} \index{Environment@{Environment}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Environment()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Environment\+Type\& Environment (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the environment. Definition at line 113 of file reward\+\_\+clipping.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a59cc43eb892c46ea7c50e18fb78b9172}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Environment@{Environment}} \index{Environment@{Environment}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Environment()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Environment\+Type\& Environment (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the environment. Definition at line 115 of file reward\+\_\+clipping.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_aa9f537249fa0c1e62b38197996ab4c6a}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Initial\+Sample@{Initial\+Sample}} \index{Initial\+Sample@{Initial\+Sample}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Initial\+Sample()} {\footnotesize\ttfamily \textbf{ State} Initial\+Sample (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} The Initial\+Sample method is called by the environment to initialize the starting state. Returns whatever Initial Sample is returned by the environment. Definition at line 62 of file reward\+\_\+clipping.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a7fd056133dfd315e4bf45c408f99326f}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Is\+Terminal@{Is\+Terminal}} \index{Is\+Terminal@{Is\+Terminal}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Is\+Terminal()} {\footnotesize\ttfamily bool Is\+Terminal (\begin{DoxyParamCaption}\item[{const \textbf{ State} \&}]{state }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Checks whether given state is a terminal state. Returns the value by calling the environment method. \begin{DoxyParams}{Parameters} {\em state} & desired state. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} true if state is a terminal state, otherwise false. \end{DoxyReturn} Definition at line 74 of file reward\+\_\+clipping.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a00e2e3602d4233fc27e8674511641e68}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Max\+Reward@{Max\+Reward}} \index{Max\+Reward@{Max\+Reward}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Max\+Reward()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double Max\+Reward (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the maximum reward value. Definition at line 123 of file reward\+\_\+clipping.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a3c1ad6d51dd13323ac752a4ca1c0cfb3}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Max\+Reward@{Max\+Reward}} \index{Max\+Reward@{Max\+Reward}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Max\+Reward()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily double\& Max\+Reward (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the maximum reward value. Definition at line 125 of file reward\+\_\+clipping.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_ac054a2c9e0295beac8c7a4fabe68e563}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Min\+Reward@{Min\+Reward}} \index{Min\+Reward@{Min\+Reward}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Min\+Reward()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double Min\+Reward (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the minimum reward value. Definition at line 118 of file reward\+\_\+clipping.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a842cc3c3e49e15e90bf0e029f150cccc}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Min\+Reward@{Min\+Reward}} \index{Min\+Reward@{Min\+Reward}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Min\+Reward()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily double\& Min\+Reward (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the minimum reward value. Definition at line 120 of file reward\+\_\+clipping.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_a311ac19edc537dee94f37b7cce93d908}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Sample@{Sample}} \index{Sample@{Sample}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Sample()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double Sample (\begin{DoxyParamCaption}\item[{const \textbf{ State} \&}]{state, }\item[{const \textbf{ Action} \&}]{action, }\item[{\textbf{ State} \&}]{next\+State }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Dynamics of Environment. The rewards returned from the base environment are clipped according the maximum and minimum values specified. \begin{DoxyParams}{Parameters} {\em state} & The current state. \\ \hline {\em action} & The current action. \\ \hline {\em next\+State} & The next state. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} clipped\+Reward, Reward clipped between [min\+Reward, max\+Reward]. \end{DoxyReturn} Definition at line 88 of file reward\+\_\+clipping.\+hpp. References mlpack\+::math\+::\+Clamp\+Range(). Referenced by Reward\+Clipping$<$ Environment\+Type $>$\+::\+Sample(). \mbox{\label{classmlpack_1_1rl_1_1RewardClipping_af2bb860eaefeaa62a40f5cf940793704}} \index{mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}!Sample@{Sample}} \index{Sample@{Sample}!mlpack\+::rl\+::\+Reward\+Clipping@{mlpack\+::rl\+::\+Reward\+Clipping}} \subsubsection{Sample()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily double Sample (\begin{DoxyParamCaption}\item[{const \textbf{ State} \&}]{state, }\item[{const \textbf{ Action} \&}]{action }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Dynamics of Environment. The rewards returned from the base environment are clipped according the maximum and minimum values specified. \begin{DoxyParams}{Parameters} {\em state} & The current state. \\ \hline {\em action} & The current action. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} clipped\+Reward, Reward clipped between [min\+Reward, max\+Reward]. \end{DoxyReturn} Definition at line 106 of file reward\+\_\+clipping.\+hpp. References Reward\+Clipping$<$ Environment\+Type $>$\+::\+Sample(). The documentation for this class was generated from the following file\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/3.\+3.\+0/src/mlpack/methods/reinforcement\+\_\+learning/environment/\textbf{ reward\+\_\+clipping.\+hpp}\end{DoxyCompactItemize}