burlap.mdp.singleagent.common

Class SingleGoalPFRF

java.lang.Object

burlap.mdp.singleagent.common.SingleGoalPFRF

All Implemented Interfaces:

RewardFunction

public class SingleGoalPFRF
extends java.lang.Object
implements RewardFunction

This class defines a reward function that returns a goal reward when any grounded form of a propositional function is true in the resulting state and a default non-goal reward otherwise.

Author:

James MacGlashan

Constructor Summary

Constructors

Constructor and Description
SingleGoalPFRF(PropositionalFunction pf) Initializes the reward function to return 1 when any grounded from of pf is true in the resulting state.
SingleGoalPFRF(PropositionalFunction pf, double goalReward, double nonGoalReward) Initializes the reward function to return the specified goal reward when any grounded from of pf is true in the resulting state and the specified non-goal reward otherwise.

Method Summary

Modifier and Type	Method and Description
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.

Methods inherited from class java.lang.Object

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

Constructor Detail

SingleGoalPFRF

public SingleGoalPFRF(PropositionalFunction pf)

Initializes the reward function to return 1 when any grounded from of pf is true in the resulting state.

Parameters:

pf - the propositional function that must have a true grounded version for the goal reward to be returned.

SingleGoalPFRF

public SingleGoalPFRF(PropositionalFunction pf,
                      double goalReward,
                      double nonGoalReward)

Initializes the reward function to return the specified goal reward when any grounded from of pf is true in the resulting state and the specified non-goal reward otherwise.

Parameters:

pf - the propositional function that must have a true grounded version for the goal reward to be returned.

goalReward - the goal reward value to be returned

nonGoalReward - the non goal reward value to be returned.

Method Detail

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.