\section{Acrobot Class Reference} \label{classmlpack_1_1rl_1_1Acrobot}\index{Acrobot@{Acrobot}} Implementation of \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} game. \subsection*{Classes} \begin{DoxyCompactItemize} \item class \textbf{ State} \end{DoxyCompactItemize} \subsection*{Public Types} \begin{DoxyCompactItemize} \item enum \textbf{ Action} \{ \newline \textbf{ negative\+Torque}, \newline \textbf{ zero\+Torque}, \newline \textbf{ positive\+Torque}, \newline \textbf{ size} \} \end{DoxyCompactItemize} \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Acrobot} (const double gravity=9.\+81, const double link\+Length1=1.\+0, const double link\+Length2=1.\+0, const double link\+Mass1=1.\+0, const double link\+Mass2=1.\+0, const double link\+Com1=0.\+5, const double link\+Com2=0.\+5, const double link\+Moi=1.\+0, const double max\+Vel1=4 $\ast$\textbf{ M\+\_\+\+PI}, const double max\+Vel2=9 $\ast$\textbf{ M\+\_\+\+PI}, const double dt=0.\+2, const double done\+Reward=0, const size\+\_\+t max\+Steps=0) \begin{DoxyCompactList}\small\item\em Construct a \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} instance using the given constants. \end{DoxyCompactList}\item arma\+::colvec \textbf{ Dsdt} (arma\+::colvec state, const double torque) const \begin{DoxyCompactList}\small\item\em This is the ordinary differential equations required for estimation of next\+State through R\+K4 method. \end{DoxyCompactList}\item \textbf{ State} \textbf{ Initial\+Sample} () \begin{DoxyCompactList}\small\item\em This function does random initialization of state space. \end{DoxyCompactList}\item bool \textbf{ Is\+Terminal} (const \textbf{ State} \&state) const \begin{DoxyCompactList}\small\item\em This function checks if the acrobot has reached the terminal state. \end{DoxyCompactList}\item size\+\_\+t \textbf{ Max\+Steps} () const \begin{DoxyCompactList}\small\item\em Get the maximum number of steps allowed. \end{DoxyCompactList}\item size\+\_\+t \& \textbf{ Max\+Steps} () \begin{DoxyCompactList}\small\item\em Set the maximum number of steps allowed. \end{DoxyCompactList}\item arma\+::colvec \textbf{ Rk4} (const arma\+::colvec state, const double torque) const \begin{DoxyCompactList}\small\item\em This function calls the R\+K4 iterative method to estimate the next state based on given ordinary differential equation. \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 the \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} System. \end{DoxyCompactList}\item double \textbf{ Sample} (const \textbf{ State} \&state, const \textbf{ Action} \&action) \begin{DoxyCompactList}\small\item\em Dynamics of the \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} System. \end{DoxyCompactList}\item size\+\_\+t \textbf{ Steps\+Performed} () const \begin{DoxyCompactList}\small\item\em Get the number of steps performed. \end{DoxyCompactList}\item double \textbf{ Torque} (const \textbf{ Action} \&action) const \begin{DoxyCompactList}\small\item\em This function calculates the torque for a particular action. \end{DoxyCompactList}\item double \textbf{ Wrap} (double value, const double minimum, const double maximum) const \begin{DoxyCompactList}\small\item\em Wrap funtion is required to truncate the angle value from -\/180 to 180. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} Implementation of \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} game. \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} is a 2-\/link pendulum with only the second joint actuated. Intitially, both links point downwards. The goal is to swing the end-\/effector at a height at least the length of one link above the base. Both links can swing freely and can pass by each other, i.\+e., they don\textquotesingle{}t collide when they have the same angle. Definition at line 28 of file acrobot.\+hpp. \subsection{Member Enumeration Documentation} \mbox{\label{classmlpack_1_1rl_1_1Acrobot_a8bb1ef53467e4f61410d12822d922498}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Action@{Action}} \index{Action@{Action}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Action} {\footnotesize\ttfamily enum \textbf{ Action}} \begin{DoxyEnumFields}{Enumerator} \raisebox{\heightof{T}}[0pt][0pt]{\index{negative\+Torque@{negative\+Torque}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}}\index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!negative\+Torque@{negative\+Torque}}}\mbox{\label{classmlpack_1_1rl_1_1Acrobot_a8bb1ef53467e4f61410d12822d922498af6e2c4a274a7061460fc52bb0e8d92dd}} negative\+Torque&\\ \hline \raisebox{\heightof{T}}[0pt][0pt]{\index{zero\+Torque@{zero\+Torque}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}}\index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!zero\+Torque@{zero\+Torque}}}\mbox{\label{classmlpack_1_1rl_1_1Acrobot_a8bb1ef53467e4f61410d12822d922498a88b15afa5c5e7a209c85650230e11752}} zero\+Torque&\\ \hline \raisebox{\heightof{T}}[0pt][0pt]{\index{positive\+Torque@{positive\+Torque}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}}\index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!positive\+Torque@{positive\+Torque}}}\mbox{\label{classmlpack_1_1rl_1_1Acrobot_a8bb1ef53467e4f61410d12822d922498a4e74e4f919288406e2c194abe8873de8}} positive\+Torque&\\ \hline \raisebox{\heightof{T}}[0pt][0pt]{\index{size@{size}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}}\index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!size@{size}}}\mbox{\label{classmlpack_1_1rl_1_1Acrobot_a8bb1ef53467e4f61410d12822d922498a052a2b4924452fb4a73f2cb52b6e9d41}} size&\\ \hline \end{DoxyEnumFields} Definition at line 88 of file acrobot.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1rl_1_1Acrobot_a3bfb421378fe3713efed9d290b365821}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Acrobot@{Acrobot}} \index{Acrobot@{Acrobot}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Acrobot()} {\footnotesize\ttfamily \textbf{ Acrobot} (\begin{DoxyParamCaption}\item[{const double}]{gravity = {\ttfamily 9.81}, }\item[{const double}]{link\+Length1 = {\ttfamily 1.0}, }\item[{const double}]{link\+Length2 = {\ttfamily 1.0}, }\item[{const double}]{link\+Mass1 = {\ttfamily 1.0}, }\item[{const double}]{link\+Mass2 = {\ttfamily 1.0}, }\item[{const double}]{link\+Com1 = {\ttfamily 0.5}, }\item[{const double}]{link\+Com2 = {\ttfamily 0.5}, }\item[{const double}]{link\+Moi = {\ttfamily 1.0}, }\item[{const double}]{max\+Vel1 = {\ttfamily 4~$\ast$~\textbf{ M\+\_\+\+PI}}, }\item[{const double}]{max\+Vel2 = {\ttfamily 9~$\ast$~\textbf{ M\+\_\+\+PI}}, }\item[{const double}]{dt = {\ttfamily 0.2}, }\item[{const double}]{done\+Reward = {\ttfamily 0}, }\item[{const size\+\_\+t}]{max\+Steps = {\ttfamily 0} }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Construct a \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} instance using the given constants. \begin{DoxyParams}{Parameters} {\em gravity} & The gravity parameter. \\ \hline {\em link\+Length1} & The length of link 1. \\ \hline {\em link\+Length2} & The length of link 2. \\ \hline {\em link\+Mass1} & The mass of link 1. \\ \hline {\em link\+Mass2} & The mass of link 2. \\ \hline {\em link\+Com1} & The position of the center of mass of link 1. \\ \hline {\em link\+Com2} & The position of the center of mass of link 2. \\ \hline {\em link\+Moi} & The moments of inertia for both links. \\ \hline {\em max\+Vel1} & The max angular velocity of link1. \\ \hline {\em max\+Vel2} & The max angular velocity of link2. \\ \hline {\em dt} & The differential value. \\ \hline {\em done\+Reward} & The reward recieved by the agent on success. \\ \hline {\em max\+Steps} & The number of steps after which the episode terminates. If the value is 0, there is no limit. \\ \hline \end{DoxyParams} Definition at line 116 of file acrobot.\+hpp. \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1rl_1_1Acrobot_a781c862b1afe7d673da7025f0b2a244c}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Dsdt@{Dsdt}} \index{Dsdt@{Dsdt}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Dsdt()} {\footnotesize\ttfamily arma\+::colvec Dsdt (\begin{DoxyParamCaption}\item[{arma\+::colvec}]{state, }\item[{const double}]{torque }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} This is the ordinary differential equations required for estimation of next\+State through R\+K4 method. \begin{DoxyParams}{Parameters} {\em state} & Current \doxyref{State}{p.}{classmlpack_1_1rl_1_1Acrobot_1_1State}. \\ \hline {\em torque} & The torque Applied. \\ \hline \end{DoxyParams} Definition at line 243 of file acrobot.\+hpp. References M\+\_\+\+PI. Referenced by Acrobot\+::\+Rk4(). \mbox{\label{classmlpack_1_1rl_1_1Acrobot_aa9f537249fa0c1e62b38197996ab4c6a}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Initial\+Sample@{Initial\+Sample}} \index{Initial\+Sample@{Initial\+Sample}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Initial\+Sample()} {\footnotesize\ttfamily \textbf{ State} Initial\+Sample (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} This function does random initialization of state space. Definition at line 207 of file acrobot.\+hpp. References Acrobot\+::\+State\+::\+State(). \mbox{\label{classmlpack_1_1rl_1_1Acrobot_a7fd056133dfd315e4bf45c408f99326f}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Is\+Terminal@{Is\+Terminal}} \index{Is\+Terminal@{Is\+Terminal}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Is\+Terminal()} {\footnotesize\ttfamily bool Is\+Terminal (\begin{DoxyParamCaption}\item[{const \textbf{ State} \&}]{state }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} This function checks if the acrobot has reached the terminal state. \begin{DoxyParams}{Parameters} {\em state} & The current \doxyref{State}{p.}{classmlpack_1_1rl_1_1Acrobot_1_1State}. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} true if state is a terminal state, otherwise false. \end{DoxyReturn} Definition at line 219 of file acrobot.\+hpp. References Log\+::\+Info, Acrobot\+::\+State\+::\+Theta1(), and Acrobot\+::\+State\+::\+Theta2(). Referenced by Acrobot\+::\+Sample(). \mbox{\label{classmlpack_1_1rl_1_1Acrobot_ad8fd6d8f7581c82e73556491b79a8907}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Max\+Steps@{Max\+Steps}} \index{Max\+Steps@{Max\+Steps}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Max\+Steps()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily size\+\_\+t Max\+Steps (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the maximum number of steps allowed. Definition at line 344 of file acrobot.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1Acrobot_a64c84cebc489c6fdfd7f057e127b0aef}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Max\+Steps@{Max\+Steps}} \index{Max\+Steps@{Max\+Steps}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Max\+Steps()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily size\+\_\+t\& Max\+Steps (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Set the maximum number of steps allowed. Definition at line 346 of file acrobot.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1Acrobot_ae09ec5b585b264b14d2831e689021a5e}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Rk4@{Rk4}} \index{Rk4@{Rk4}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Rk4()} {\footnotesize\ttfamily arma\+::colvec Rk4 (\begin{DoxyParamCaption}\item[{const arma\+::colvec}]{state, }\item[{const double}]{torque }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} This function calls the R\+K4 iterative method to estimate the next state based on given ordinary differential equation. \begin{DoxyParams}{Parameters} {\em state} & The current \doxyref{State}{p.}{classmlpack_1_1rl_1_1Acrobot_1_1State}. \\ \hline {\em torque} & The torque applied. \\ \hline \end{DoxyParams} Definition at line 329 of file acrobot.\+hpp. References Acrobot\+::\+Dsdt(). Referenced by Acrobot\+::\+Sample(). \mbox{\label{classmlpack_1_1rl_1_1Acrobot_a311ac19edc537dee94f37b7cce93d908}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Sample@{Sample}} \index{Sample@{Sample}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \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 the \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} System. To get reward and next state based on current state and current action. Always return -\/1 reward. \begin{DoxyParams}{Parameters} {\em state} & The current \doxyref{State}{p.}{classmlpack_1_1rl_1_1Acrobot_1_1State}. \\ \hline {\em action} & The action taken. \\ \hline {\em next\+State} & The next state. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} reward, it\textquotesingle{}s always -\/1.\+0. \end{DoxyReturn} The value of angular velocity is bounded in min and max value. Definition at line 154 of file acrobot.\+hpp. References Acrobot\+::\+State\+::\+Angular\+Velocity1(), Acrobot\+::\+State\+::\+Angular\+Velocity2(), mlpack\+::math\+::\+Clamp\+Range(), Acrobot\+::\+Is\+Terminal(), M\+\_\+\+PI, Acrobot\+::\+Rk4(), Acrobot\+::\+State\+::\+Theta1(), Acrobot\+::\+State\+::\+Theta2(), Acrobot\+::\+Torque(), and Acrobot\+::\+Wrap(). Referenced by Acrobot\+::\+Sample(). \mbox{\label{classmlpack_1_1rl_1_1Acrobot_af2bb860eaefeaa62a40f5cf940793704}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Sample@{Sample}} \index{Sample@{Sample}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \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 the \doxyref{Acrobot}{p.}{classmlpack_1_1rl_1_1Acrobot} System. To get reward and next state based on current state and current action. This function calls the Sample function to estimate the next state return reward for taking a particular action. \begin{DoxyParams}{Parameters} {\em state} & The current \doxyref{State}{p.}{classmlpack_1_1rl_1_1Acrobot_1_1State}. \\ \hline {\em action} & The action taken. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} next\+State The next state. \end{DoxyReturn} Definition at line 198 of file acrobot.\+hpp. References Acrobot\+::\+Sample(). \mbox{\label{classmlpack_1_1rl_1_1Acrobot_a5fe06563064ebcee88c593e1673f03d4}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Steps\+Performed@{Steps\+Performed}} \index{Steps\+Performed@{Steps\+Performed}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Steps\+Performed()} {\footnotesize\ttfamily size\+\_\+t Steps\+Performed (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the number of steps performed. Definition at line 341 of file acrobot.\+hpp. \mbox{\label{classmlpack_1_1rl_1_1Acrobot_ae12a0a80a61e21f6e1b722f4ad7d0b81}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Torque@{Torque}} \index{Torque@{Torque}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Torque()} {\footnotesize\ttfamily double Torque (\begin{DoxyParamCaption}\item[{const \textbf{ Action} \&}]{action }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} This function calculates the torque for a particular action. 0 \+: negative torque, 1 \+: zero torque, 2 \+: positive torque. \begin{DoxyParams}{Parameters} {\em action} & Action taken. \\ \hline \end{DoxyParams} Definition at line 316 of file acrobot.\+hpp. References mlpack\+::math\+::\+Random(). Referenced by Acrobot\+::\+Sample(). \mbox{\label{classmlpack_1_1rl_1_1Acrobot_a9f977aba34c92e5f5f9249d8738ec85a}} \index{mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}!Wrap@{Wrap}} \index{Wrap@{Wrap}!mlpack\+::rl\+::\+Acrobot@{mlpack\+::rl\+::\+Acrobot}} \subsubsection{Wrap()} {\footnotesize\ttfamily double Wrap (\begin{DoxyParamCaption}\item[{double}]{value, }\item[{const double}]{minimum, }\item[{const double}]{maximum }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Wrap funtion is required to truncate the angle value from -\/180 to 180. This function will make sure that value will always be between minimum to maximum. \begin{DoxyParams}{Parameters} {\em value} & Scalar value to wrap. \\ \hline {\em minimum} & Minimum range of wrap. \\ \hline {\em maximum} & Maximum range of wrap. \\ \hline \end{DoxyParams} Definition at line 292 of file acrobot.\+hpp. Referenced by Acrobot\+::\+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.\+2/src/mlpack/methods/reinforcement\+\_\+learning/environment/\textbf{ acrobot.\+hpp}\end{DoxyCompactItemize}