/*SampleNextStateWithEvaluation(...) does the following tasks:
* 1. sample next MDPconfiguration if it is a pcase
* 2. if not, it will directly return nex MDPconfiguration
* 3. Evaluation on the next MDPconfiguration will also be done
*/
//assume there is no no-deterministic choice
//as we assume there is only deterministic choices, including probabilistic choices. Hence, if the list.length=1, corresponding to a normal step, if not, then, it should be a probability distribution, hence, a simple sampling process will be taken to evaluate the next step. Here, we assume there is no loop. and the whole precess is bounded.
public bool sampleNextStateWithEvaluation(MDPConfiguration currentConfiguration)
{
numberOfTotalVisitedStates++;
bool evaluationResult;
currentStep++;
if (currentConfiguration.IsDeadLock || currentStep > boundedStep)
{
return(false);
}
MDPConfiguration[] list = currentConfiguration.MakeOneMoveLocal().ToArray();
if (list.Length == 0)
{
return(false);
}
if (list.Length == 1)
{
MDPConfiguration step = list[0];
ExpressionValue v = EvaluatorDenotational.Evaluate(ReachableStateCondition, step.GlobalEnv);
evaluationResult = (v as BoolConstant).Value;
return(evaluationResult || sampleNextStateWithEvaluation(step));
}
double value = random.NextDouble();
double sum = 0;
foreach (MDPConfiguration configuration in list)
{
sum += configuration.Probability;
}
double accumulation = 0;
foreach (MDPConfiguration configuration in list)
{
double preaccumulation = accumulation;
accumulation += (configuration.Probability / sum);
if (value > preaccumulation && value <= accumulation)
{
ExpressionValue v = EvaluatorDenotational.Evaluate(ReachableStateCondition, configuration.GlobalEnv);
evaluationResult = (v as BoolConstant).Value;
return(evaluationResult || sampleNextStateWithEvaluation(configuration));
}
}
// the folllowing codes will never happen. -----Should be.
return(false);
}
// public Expression ReachableStateCondition;
//status=true means: single trial, otherwise, mutliple trails
public SimulationNoMDP(MDPConfiguration initialConfiguration, Expression reachableStateCondition)
{
this.intialConfiguration = initialConfiguration;
this.ReachableStateCondition = reachableStateCondition;
this.random = new Random();
}
