private void doValueIteration(BinaryDecisionTree bdt)
{
List <double> maxV = bdt.ReturnValue(true);
List <double> minV = bdt.ReturnValue(false);
List <Set <int> > abstractMap = bdt.ReturnLeaves();
double tmp;
int maxvcount = maxV.Count;
double diff = 1.0;
double epsilon = 0.1;
while (diff > epsilon)
{
diff = 0.0;
for (int k = 0; k < maxvcount; k++)
{
tmp = doLocalValueIteration(k, abstractMap, maxV, true);
diff = Math.Max(diff, Math.Abs(tmp - maxV[k]));
maxV[k] = tmp;
tmp = doLocalValueIteration(k, abstractMap, minV, false);
diff = Math.Max(diff, Math.Abs(tmp - minV[k]));
minV[k] = tmp;
}
}
for (int k = 0; k < maxvcount; k++)
{
System.Console.WriteLine("maxv " + maxV[k] + " minv " + minV[k]);
}
// Need to update the maxValue as well as minValue in the tree
bdt = bdt.UpdateMaxMin(maxV, minV, abstractMap);
}
private CompoundTerm ChooseAction(Sequence <Action> actions, IState iState)
{
TransitionProperties tp;
int targetId = -1;
List <double> MaxV = bdt.ReturnValue(true);
List <double> MinV = bdt.ReturnValue(false);
List <Set <int> > abstractMap = bdt.ReturnLeaves();
Sequence <Pair <int, Action> > cumulActSum = Sequence <Pair <int, Action> > .EmptySequence;
double epsilon = 0.1;
Dictionary <int, int> sumTarget = new Dictionary <int, int>();
Action maxAct = null;
int targetAbsId = -1;
int sum = 0;
UpdateRequirementMaps(actions, iState);
Set <Action> newStateActs = new Set <Action>();
Set <Action> oldActs = new Set <Action>(actions.Head);
foreach (Action a in actions)
{
int tState = this.modelProgram.GetTargetState(iState, a, null, out tp).GetHashCode();
targetAbsId = findAbstractId(tState, abstractMap);
if (targetAbsId == -1)
{
newStateActs = newStateActs.Add(a);
}
else
{
sum = sum + (int)(MaxV[targetAbsId] * Math.Pow(10.0, 9.0));
Pair <int, Action> np = new Pair <int, Action>(sum, a);
sumTarget.Add(sum, targetAbsId);
cumulActSum = cumulActSum.AddLast(np);
}
}
if (!newStateActs.IsEmpty)
{
maxAct = newStateActs.Choose();
System.Console.WriteLine("new action in new state " + maxAct.ToString());
return(maxAct);
}
else
{
Random rndNumbers = new Random();
int rndNumber = rndNumbers.Next(sum);
System.Console.WriteLine(sum + " " + rndNumber);
foreach (Pair <int, Action> np in cumulActSum)
{
System.Console.WriteLine(np.First + " " + np.Second.ToString());
if (rndNumber <= np.First)
{
maxAct = np.Second;
targetId = sumTarget[np.First];
break;
}
targetId = sumTarget[np.First];
maxAct = np.Second;
}
System.Console.WriteLine("old action in old state " + maxAct.ToString());
}
// Adaptive Refinement
if (MaxV[targetId] - MinV[targetId] > epsilon)
{
if (i < requirementProperties.Count)
{
string s1 = requirementProperties[i++];
bdt = bdt.Refine(s1, requireEnabledStateMap[s1]);
bdt.PrintTree(0);
}
}
return(maxAct);
}
private void doValueIteration(BinaryDecisionTree bdt)
{
List<double> maxV = bdt.ReturnValue(true);
List<double> minV = bdt.ReturnValue(false);
List<Set<int>> abstractMap = bdt.ReturnLeaves();
double tmp;
int maxvcount = maxV.Count;
double diff = 1.0;
double epsilon = 0.1;
while (diff > epsilon)
{
diff = 0.0;
for (int k = 0; k < maxvcount;k++)
{
tmp = doLocalValueIteration(k, abstractMap, maxV, true);
diff = Math.Max(diff, Math.Abs(tmp - maxV[k]));
maxV[k] = tmp;
tmp = doLocalValueIteration(k, abstractMap, minV, false);
diff = Math.Max(diff, Math.Abs(tmp - minV[k]));
minV[k] = tmp;
}
}
for (int k = 0; k < maxvcount; k++)
{
System.Console.WriteLine("maxv "+ maxV[k]+ " minv "+ minV[k]);
}
// Need to update the maxValue as well as minValue in the tree
bdt = bdt.UpdateMaxMin(maxV, minV, abstractMap);
}