burlap.behavior.singleagent.options

Class OptionEvaluatingRF

java.lang.Object

burlap.behavior.singleagent.options.OptionEvaluatingRF

All Implemented Interfaces:

RewardFunction

public class OptionEvaluatingRF
extends java.lang.Object
implements RewardFunction

This class is a reward function that accepts a reward function for primitive actions and returns that when the query action is a primitive. If the query action is a option it return the cumulative reward from the options last execution using the assumption that any options that need evaluating have been set to internally keep track of their reward after each successive application. It also is assumed that those options are using the same reward function as the inputed primitive RF This is useful for planners that would want to execute the option and evaluate the reward afterwards

Author:

James MacGlashan

Constructor Summary

Constructors

Constructor and Description
OptionEvaluatingRF(RewardFunction rf) Initializes.

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

Constructor Detail

OptionEvaluatingRF

public OptionEvaluatingRF(RewardFunction rf)

Initializes.

Parameters:

rf - the source primitive action reward function for the MDP

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.