@Override
public int[] act(final double returns[], final int num) {
int[] chosen = null;
if (num > returns.length) {
chosen = new int[returns.length];
} else {
chosen = new int[num];
}
final ArrayList<Double> values = new ArrayList<Double>();
final ArrayList<Integer> indices = new ArrayList<Integer>();
for (int i = 0; i < returns.length; i++) {
values.add(returns[i]);
indices.add(i);
}
int index = -1;
for (int i = 0; i < chosen.length; i++) {
index = choosing.internalAct(Utils.toArray(values));
chosen[i] = indices.get(index).intValue();
// remove the chosen action and its return
values.remove(index);
indices.remove(index);
}
choosing.updateEpsilon();
return chosen;
}
@Override
public String toString() {
String s = super.toString();
s += "\n" + Utils.indent(choosing.toString());
return s;
}
public Object protoClone() {
try {
final EpsilonGreedyMultiActionChoosingPolicy copy =
(EpsilonGreedyMultiActionChoosingPolicy) clone();
copy.choosing = (EpsilonGreedyActionChoosingPolicy) choosing.protoClone();
return copy;
} catch (final CloneNotSupportedException e) {
e.printStackTrace();
return null;
}
}
public void reset() {
choosing.reset();
}
public void setup(final ParameterDatabase parameters, final Parameter base) {
choosing.setup(parameters, base);
choosing.initialize();
}
