burlap.domain.singleagent.cartpole

Class CartPoleDomain.CartPoleRewardFunction

java.lang.Object

burlap.domain.singleagent.cartpole.CartPoleDomain.CartPoleRewardFunction

All Implemented Interfaces:

RewardFunction

Enclosing class:

CartPoleDomain

public static class CartPoleDomain.CartPoleRewardFunction
extends java.lang.Object
implements RewardFunction

A default reward function for this task. Returns 0 everywhere except at fail conditions, which return -1 and are defined by the agent reaching the end of the track or by the angle of the pole being grater than some threshold (default 12 degrees or about 0.2 radians).

Author:

James MacGlashan

Constructor Summary

Constructors

Constructor and Description
CartPoleRewardFunction() Initializes with max pole angle threshold of 12 degrees (about 0.2 radians)
CartPoleRewardFunction(double maxAbsoluteAngleInRadians) Initializes with a max pole angle as specified in radians

Method Summary

Modifier and Type	Method and Description
double	getHalfTrackLength()
double	getMaxAbsoluteAngle()
double	reward(State s, Action a, State sprime) Returns the reward received when action a is executed in state s and the agent transitions to state sprime.
void	setHalfTrackLength(double halfTrackLength)
void	setMaxAbsoluteAngle(double maxAbsoluteAngle)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CartPoleRewardFunction

public CartPoleRewardFunction()

Initializes with max pole angle threshold of 12 degrees (about 0.2 radians)

CartPoleRewardFunction

public CartPoleRewardFunction(double maxAbsoluteAngleInRadians)

Initializes with a max pole angle as specified in radians

Parameters:

maxAbsoluteAngleInRadians - the maximum pole angle that causes task failure.

Method Detail

getMaxAbsoluteAngle

public double getMaxAbsoluteAngle()

setMaxAbsoluteAngle

public void setMaxAbsoluteAngle(double maxAbsoluteAngle)

getHalfTrackLength

public double getHalfTrackLength()

setHalfTrackLength

public void setHalfTrackLength(double halfTrackLength)

reward

public double reward(State s,
                     Action a,
                     State sprime)

Description copied from interface: RewardFunction

Returns the reward received when action a is executed in state s and the agent transitions to state sprime.

Specified by:

reward in interface RewardFunction

Parameters:

s - the state in which the action was executed

a - the action executed

sprime - the state to which the agent transitioned

Returns:

the reward received when action a is executed in state s and the agent transitions to state sprime.