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, setPlannerprotected 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()
IRLRequestisValid in class IRLRequestpublic void setFeatureGenerator(DenseStateFeatures stateFeaturesGenerator)
public void setExpertEpisodes(java.util.List<Episode> episodeList)
setExpertEpisodes in class IRLRequestpublic 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 IRLRequestpublic StateGenerator getStartStateGenerator()
public double getEpsilon()
public int getMaxIterations()
public int getPolicyCount()
public double[] getTHistory()
public boolean getUsingMaxMargin()