public class ApprenticeshipLearningRequest extends IRLRequest
Modifier and Type | Field and Description |
---|---|
static double |
DEFAULT_EPSILON |
static int |
DEFAULT_MAXITERATIONS |
static int |
DEFAULT_POLICYCOUNT |
static boolean |
DEFAULT_USEMAXMARGIN |
protected double |
epsilon
The maximum feature score to cause termination of Apprenticeship learning
|
protected DenseStateFeatures |
featureGenerator
The state feature generator that turns a state into a feature vector on which the reward function is assumed to be modeled
|
protected int |
maxIterations
The maximum number of iterations of apprenticeship learning
|
protected int |
policyCount
The maximum number of times a policy is rolled out and evaluated
|
protected StateGenerator |
startStateGenerator
The initial state generator that models the initial states from which the expert trajectories were drawn
|
protected double[] |
tHistory
the history of scores across each reward function improvement
|
protected boolean |
useMaxMargin
If true, use the full max margin method (expensive); if false, use the cheaper projection method
|
domain, expertEpisodes, gamma, planner
Constructor and Description |
---|
ApprenticeshipLearningRequest() |
ApprenticeshipLearningRequest(SADomain domain,
Planner planner,
DenseStateFeatures featureGenerator,
java.util.List<Episode> expertEpisodes,
StateGenerator startStateGenerator) |
Modifier and Type | Method and Description |
---|---|
double |
getEpsilon() |
java.util.List<Episode> |
getExpertEpisodes() |
DenseStateFeatures |
getFeatureGenerator() |
int |
getMaxIterations() |
int |
getPolicyCount() |
StateGenerator |
getStartStateGenerator() |
double[] |
getTHistory() |
boolean |
getUsingMaxMargin() |
protected void |
initDefaults() |
boolean |
isValid()
Returns true if this request object has valid data members set; false otherwise.
|
void |
setEpsilon(double epsilon) |
void |
setExpertEpisodes(java.util.List<Episode> episodeList) |
void |
setFeatureGenerator(DenseStateFeatures stateFeaturesGenerator) |
void |
setMaxIterations(int maxIterations) |
void |
setPolicyCount(int policyCount) |
void |
setStartStateGenerator(StateGenerator startStateGenerator) |
void |
setTHistory(double[] tHistory) |
void |
setUsingMaxMargin(boolean useMaxMargin) |
getDomain, getGamma, getPlanner, setDomain, setGamma, setPlanner
protected DenseStateFeatures featureGenerator
protected StateGenerator startStateGenerator
protected double epsilon
protected int maxIterations
protected int policyCount
protected double[] tHistory
protected boolean useMaxMargin
public static final double DEFAULT_EPSILON
public static final int DEFAULT_MAXITERATIONS
public static final int DEFAULT_POLICYCOUNT
public static final boolean DEFAULT_USEMAXMARGIN
public ApprenticeshipLearningRequest()
public ApprenticeshipLearningRequest(SADomain domain, Planner planner, DenseStateFeatures featureGenerator, java.util.List<Episode> expertEpisodes, StateGenerator startStateGenerator)
protected void initDefaults()
public boolean isValid()
IRLRequest
isValid
in class IRLRequest
public void setFeatureGenerator(DenseStateFeatures stateFeaturesGenerator)
public void setExpertEpisodes(java.util.List<Episode> episodeList)
setExpertEpisodes
in class IRLRequest
public void setStartStateGenerator(StateGenerator startStateGenerator)
public void setEpsilon(double epsilon)
public void setMaxIterations(int maxIterations)
public void setPolicyCount(int policyCount)
public void setTHistory(double[] tHistory)
public void setUsingMaxMargin(boolean useMaxMargin)
public DenseStateFeatures getFeatureGenerator()
public java.util.List<Episode> getExpertEpisodes()
getExpertEpisodes
in class IRLRequest
public StateGenerator getStartStateGenerator()
public double getEpsilon()
public int getMaxIterations()
public int getPolicyCount()
public double[] getTHistory()
public boolean getUsingMaxMargin()