public TaskDescription getTaskSpec() {
int numCompartments = arm.getCompartments().size();
int numFood = allFood.size();
int numStateVars = 2 + 4 * (2 * numCompartments + numFood);
int numActionVars = 3 * numCompartments;
return new TaskDescription(numStateVars, numActionVars);
}
public ChoiceTracker(ChoiceSpec spec) {
subObjectives = new HashSet<ObjectiveTracker>();
for (ObjectiveSpec os : spec.getObjective()) {
subObjectives.add(makeObjectiveTracker(os));
}
selected = null;
accomplished = false;
}
private String makeTaskSpec() {
double minXPos = -12.0d;
double maxXPos = 12.0d;
double minYPos = -12.0d;
double maxYPos = 6.0d;
double minVel = -1.0d;
double maxVel = 1.0d;
double minAction = 0.0d;
double maxAction = 1.0d;
TaskDescription ts = getTaskSpec();
TaskSpecVRLGLUE3 theTaskSpecObject = new TaskSpecVRLGLUE3();
theTaskSpecObject.setEpisodic();
theTaskSpecObject.setDiscountFactor(1.0d);
// Angle of the arm
theTaskSpecObject.addContinuousObservation(new DoubleRange(-4.0d * Math.PI, 4.0d * Math.PI));
// Angular Velocity
theTaskSpecObject.addContinuousObservation(new DoubleRange(-1.0d, 1.0d));
// Now we want to add the variable for all the compartments
for (int i = 0; i < 4 * (2 * arm.getCompartments().size() + allFood.size()); i++) {
if (i % 4 == 0) {
theTaskSpecObject.addContinuousObservation(new DoubleRange(minXPos, maxXPos));
}
if (i % 4 == 1) {
theTaskSpecObject.addContinuousObservation(new DoubleRange(minYPos, maxYPos));
}
if (i % 4 == 2 || i % 4 == 3) {
theTaskSpecObject.addContinuousObservation(new DoubleRange(minVel, maxVel));
}
}
int NDA = 8;
if (useDiscreteActions) {
theTaskSpecObject.addDiscreteAction(new IntRange(0, NDA - 1));
} else {
theTaskSpecObject.addContinuousAction(
(new DoubleRange(minAction, maxAction, ts.getNumActionVariables())));
}
theTaskSpecObject.setRewardRange(new DoubleRange(-1, 20));
String newTaskSpecString = theTaskSpecObject.toTaskSpec();
TaskSpec.checkTaskSpec(newTaskSpecString);
return newTaskSpecString;
}