burlap.behavior.singleagent.vfa

Class ApproximationResult

java.lang.Object

burlap.behavior.singleagent.vfa.ApproximationResult

public class ApproximationResult
extends java.lang.Object

A list associating a predicted value that was generated from a list of state features and the weights for those features. Note that the predicted value does *not* have to be a linear combination of the state features and the weights, so it may not be possible to reconstruct the predicted value from the features and weights alone.

Author:

James MacGlashan

Field Summary

Fields

Modifier and Type	Field and Description
java.util.List<FunctionWeight>	functionWeights The function weights used to produce the predicted value.
double	predictedValue The predicted valued
java.util.List<StateFeature>	stateFeatures The state features used to produce the predicted value.

Constructor Summary

Constructors

Constructor and Description
ApproximationResult(double predictedValue, java.util.List<StateFeature> stateFeatures, java.util.List<FunctionWeight> functionWeights) Initializes

Method Summary

Methods inherited from class java.lang.Object

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

Field Detail

predictedValue

public double predictedValue

The predicted valued

stateFeatures

public java.util.List<StateFeature> stateFeatures

The state features used to produce the predicted value.

functionWeights

public java.util.List<FunctionWeight> functionWeights

The function weights used to produce the predicted value.

Constructor Detail

ApproximationResult

public ApproximationResult(double predictedValue,
                   java.util.List<StateFeature> stateFeatures,
                   java.util.List<FunctionWeight> functionWeights)

Initializes

Parameters:

predictedValue - the predicted value

stateFeatures - the state features used to produce the predicted value.

functionWeights - the function weights used to produce the predicted value.