MountainCar Class Reference

Implementation of Mountain Car task. More...

Classes
class	State
	Implementation of state of Mountain Car. More...

Public Types
enum	Action {   backward ,   stop ,   forward ,   size }
	Implementation of action of Mountain Car. More...

Public Member Functions
	MountainCar (const double positionMin=-1.2, const double positionMax=0.6, const double positionGoal=0.5, const double velocityMin=-0.07, const double velocityMax=0.07, const double doneReward=0)
	Construct a Mountain Car instance using the given constant. More...
State	InitialSample () const
	Initial position is randomly generated within [-0.6, -0.4]. More...
bool	IsTerminal (const State &state) const
	Whether given state is a terminal state. More...
double	Sample (const State &state, const Action &action, State &nextState) const
	Dynamics of Mountain Car. More...
double	Sample (const State &state, const Action &action) const
	Dynamics of Mountain Car. More...

Detailed Description

Implementation of Mountain Car task.

Definition at line 27 of file mountain_car.hpp.

Member Enumeration Documentation

Action

enum Action

Implementation of action of Mountain Car.

Enumerator
backward
stop
forward
size	Track the size of the action space.

Definition at line 78 of file mountain_car.hpp.

Constructor & Destructor Documentation

MountainCar()

MountainCar ( const double  positionMin = -1.2, const double  positionMax = 0.6, const double  positionGoal = 0.5, const double  velocityMin = -0.07, const double  velocityMax = 0.07, const double  doneReward = 0  )

inline

Construct a Mountain Car instance using the given constant.

Parameters

positionMin	Minimum legal position.
positionMax	Maximum legal position.
positionGoal	Final target position.
velocityMin	Minimum legal velocity.
velocityMax	Maximum legal velocity.

Definition at line 97 of file mountain_car.hpp.

Member Function Documentation

InitialSample()

State InitialSample ( ) const

inline

Initial position is randomly generated within [-0.6, -0.4].

Initial velocity is 0.

Returns

Initial state for each episode.

Definition at line 172 of file mountain_car.hpp.

References MountainCar::State::Position(), and MountainCar::State::Velocity().

IsTerminal()

bool IsTerminal ( const State &  state ) const

inline

Whether given state is a terminal state.

Parameters

state

desired state.

Returns

true if state is a terminal state, otherwise false.

Definition at line 186 of file mountain_car.hpp.

References MountainCar::State::Position().

Referenced by MountainCar::Sample().

Sample() [1/2]

double Sample ( const State &  state, const Action &  action, State &  nextState  ) const

inline

Dynamics of Mountain Car.

Get reward and next state based on current state and current action.

Parameters

state	The current state.
action	The current action.
nextState	The next state.

Returns

reward, it's always -1.0.

If done is true , it means that car has reached its goal. To make sure that the agent learns this, we will give some positive reward to the agent. If the agent doesn't reach the terminal state, then we will give a -1.0 reward to penalize the agent to take that step.

Definition at line 120 of file mountain_car.hpp.

References MountainCar::IsTerminal(), MountainCar::State::Position(), and MountainCar::State::Velocity().

Referenced by MountainCar::Sample().

Sample() [2/2]

double Sample ( const State &  state, const Action &  action  ) const

inline

Dynamics of Mountain Car.

Get reward based on current state and current action.

Parameters

state	The current state.
action	The current action.

Returns

reward, it's always -1.0.

Definition at line 160 of file mountain_car.hpp.

References MountainCar::Sample().

---

The documentation for this class was generated from the following file:

• /home/ryan/src/mlpack.org/_src/mlpack-3.1.1/src/mlpack/methods/reinforcement_learning/environment/mountain_car.hpp