Package repast.simphony.parameter.optimizer

Class AnnealingAdvancementChooser

java.lang.Object

repast.simphony.parameter.optimizer.HillClimber

repast.simphony.parameter.optimizer.AnnealingAdvancementChooser

All Implemented Interfaces:

AdvancementChooser

public class AnnealingAdvancementChooser
extends HillClimber

Field Summary

Fields

Modifier and Type	Field	Description
protected CoolingSchedule	coolingSchedule
static double	DEFAULT_INITIAL_TEMP
protected boolean	jumped
protected double	maxTemp
protected AdvanceType	preJumpAdvance
protected double	preJumpRunResult

Fields inherited from class repast.simphony.parameter.optimizer.HillClimber

centerValue, checkingLocal, forwardValid, forwardValue, lastSetter, lastValue

Constructor Summary

Constructors

Constructor	Description
AnnealingAdvancementChooser()
AnnealingAdvancementChooser(CoolingSchedule schedule, double initialTemp)

Method Summary

Modifier and Type	Method	Description
AdvanceType	chooseAdvancement(ParameterSetter init, AdvanceType lastType, double runResult)	This performs the hill climbing algorithm.
protected boolean	chooseRandom()
protected double	getRandom()
boolean	shouldRevert(double runResult)	Returns true when the previous run's value was greater than runResult or when we're exploring the local space to figure out which direction to go.

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_INITIAL_TEMP

public static final double DEFAULT_INITIAL_TEMP

See Also:

Constant Field Values

coolingSchedule

protected CoolingSchedule coolingSchedule

maxTemp

protected double maxTemp

jumped

protected boolean jumped

preJumpAdvance

protected AdvanceType preJumpAdvance

preJumpRunResult

protected double preJumpRunResult

Constructor Detail

AnnealingAdvancementChooser

public AnnealingAdvancementChooser()

AnnealingAdvancementChooser

public AnnealingAdvancementChooser(CoolingSchedule schedule,
                                   double initialTemp)

Method Detail

chooseAdvancement

public AdvanceType chooseAdvancement(ParameterSetter init,
                                     AdvanceType lastType,
                                     double runResult)

Description copied from class: HillClimber

This performs the hill climbing algorithm. In the best case it will traverse the space by (assuming we've just chosen a new parameter):

• Explore the local space to find which direction to follow. It first will explore to the right (FORWARD) of the current position, then to the left (BACKWARD).
• Next it will move whichever direction is best of left, right, and the neither (if we're at a peak). If we're on a peak it will return AdvanceType.SWITCH.

Because of the implementation, this may result in a single spot being executed multiple times in order. Also, this handles the border cases where it cannot move forwards or backwards (but wishes to) by switching.

Specified by:

chooseAdvancement in interface AdvancementChooser

Overrides:

chooseAdvancement in class HillClimber

Parameters:

init - the current setter

lastType - the last executed parameter command

runResult - the last run's value

Returns:

the action to perform

shouldRevert

public boolean shouldRevert(double runResult)

Description copied from class: HillClimber

Returns true when the previous run's value was greater than runResult or when we're exploring the local space to figure out which direction to go.

Specified by:

shouldRevert in interface AdvancementChooser

Overrides:

shouldRevert in class HillClimber

Parameters:

runResult - the result of the previous run

Returns:

if we should revert to the previous space

chooseRandom

protected boolean chooseRandom()

getRandom

protected double getRandom()