burlap.behavior.singleagent.planning.deterministic

Class UniformPlusGoalRF

java.lang.Object

burlap.behavior.singleagent.planning.deterministic.UniformPlusGoalRF

All Implemented Interfaces:

RewardFunction

public class UniformPlusGoalRF
extends java.lang.Object
implements RewardFunction

This Reward function returns a uniform cost (-1) for all transitions that do not transition to a goal state and 0 on transitions to the goal state. Goal states are indicated by a StateConditionTest class.

Author:

James MacGlashan

Field Summary

Fields

Modifier and Type	Field and Description
protected StateConditionTest	gc

Constructor Summary

Constructors

Constructor and Description
UniformPlusGoalRF(StateConditionTest gc) Sets the reward function to return 0 when transition to states that satisfy gc, and -1 otherwise

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

gc

protected StateConditionTest gc

Constructor Detail

UniformPlusGoalRF

public UniformPlusGoalRF(StateConditionTest gc)

Sets the reward function to return 0 when transition to states that satisfy gc, and -1 otherwise

Parameters:

gc - when gc returns true, it indicates a goal state.

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.