burlap.domain.singleagent.frostbite

Class FrostbiteRF

java.lang.Object

burlap.domain.singleagent.frostbite.FrostbiteRF

All Implemented Interfaces:

RewardFunction

public class FrostbiteRF
extends java.lang.Object
implements RewardFunction

Author:

Phillipe Morere

Field Summary

Fields

Modifier and Type	Field and Description
double	activatedPlatformReward
double	defaultReward
double	goalReward
double	lostReward

Constructor Summary

Constructors

Constructor and Description
FrostbiteRF(Domain domain)

Method Summary

Methods

Modifier and Type	Method and Description
double	reward(State s, GroundedAction a, State sprime) Returns the reward received when action a is executed in state s and the agent transitions to state sprime.

Methods inherited from class java.lang.Object

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

Field Detail

goalReward

public double goalReward

lostReward

public double lostReward

activatedPlatformReward

public double activatedPlatformReward

defaultReward

public double defaultReward

Constructor Detail

FrostbiteRF

public FrostbiteRF(Domain domain)

Method Detail

reward

public double reward(State s,
            GroundedAction 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.