burlap.behavior.learningrate

Class ConstantLR

java.lang.Object

burlap.behavior.learningrate.ConstantLR

All Implemented Interfaces:

LearningRate

public class ConstantLR
extends java.lang.Object
implements LearningRate

A class for specifying a constant learning rate that never changes.

Author:

James MacGlashan

Field Summary

Fields

Modifier and Type	Field and Description
double	learningRate

Constructor Summary

Constructors

Constructor and Description
ConstantLR() Constructs constant learning rate of 0.1
ConstantLR(java.lang.Double learningRate) Constructs a constant learning rate for the given value

Method Summary

Modifier and Type	Method and Description
double	peekAtLearningRate(int featureId) A method for looking at the current learning rate for a state (-action) feature without having it altered.
double	peekAtLearningRate(State s, Action ga) A method for looking at the current learning rate for a state-action pair without having it altered.
double	pollLearningRate(int agentTime, int featureId) A method for returning the learning rate for a given state (-action) feature and then decaying the learning rate as defined by this class.
double	pollLearningRate(int agentTime, State s, Action ga) A method for returning the learning rate for a given state action pair and then decaying the learning rate as defined by this class.
void	resetDecay() Causes any learnign rate decay to reset to where it started.

Methods inherited from class java.lang.Object

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

Field Detail

learningRate

public double learningRate

Constructor Detail

ConstantLR

public ConstantLR()

Constructs constant learning rate of 0.1

ConstantLR

public ConstantLR(java.lang.Double learningRate)

Constructs a constant learning rate for the given value

Parameters:

learningRate - the constant learning rate to use

Method Detail

peekAtLearningRate

public double peekAtLearningRate(State s,
                                 Action ga)

Description copied from interface: LearningRate

A method for looking at the current learning rate for a state-action pair without having it altered.

Specified by:

peekAtLearningRate in interface LearningRate

Parameters:

s - the state for which the learning rate should be returned

ga - the action from which the learning rate should be returned

Returns:

the current learning rate for the given state-action pair

pollLearningRate

public double pollLearningRate(int agentTime,
                               State s,
                               Action ga)

Description copied from interface: LearningRate

A method for returning the learning rate for a given state action pair and then decaying the learning rate as defined by this class.

Specified by:

pollLearningRate in interface LearningRate

Parameters:

agentTime - the time index of the agent when polling.

s - the state for which the learning rate should be returned

ga - the action from which the learning rate should be returned

Returns:

the current learning rate for the given state-action pair

resetDecay

public void resetDecay()

Description copied from interface: LearningRate

Causes any learnign rate decay to reset to where it started.

Specified by:

resetDecay in interface LearningRate

peekAtLearningRate

public double peekAtLearningRate(int featureId)

Description copied from interface: LearningRate

A method for looking at the current learning rate for a state (-action) feature without having it altered.

Specified by:

peekAtLearningRate in interface LearningRate

Parameters:

featureId - the state feature for which the learning rate should be returned

Returns:

the current learning rate for the given state feature-action pair

pollLearningRate

public double pollLearningRate(int agentTime,
                               int featureId)

Description copied from interface: LearningRate

A method for returning the learning rate for a given state (-action) feature and then decaying the learning rate as defined by this class.

Specified by:

pollLearningRate in interface LearningRate

Parameters:

agentTime - the time index of the agent when polling.

featureId - the state feature for which the learning rate should be returned

Returns:

the current learning rate for the given state feature-action pair