public void Evaluate(
IPolicy <TState, TAction> policy,
IRewarder <TState, TAction> rewarder,
int sweepLimit = -1)
{
var numSweeps = 0;
var largestValueChange = 0.0;
do
{
largestValueChange = 0.0;
foreach (var state in _problem.AllStates())
{
var originalValue = Value(state);
var newValue = CalculateValue(state, policy, rewarder);
_values[state] = newValue;
var valueChange = Math.Abs(originalValue - newValue);
if (valueChange > largestValueChange)
{
largestValueChange = valueChange;
}
}
if (sweepLimit > 0 && ++numSweeps == sweepLimit)
{
break;
}
} while (largestValueChange > 0.000001);
}
public static GreedyPolicy <TState, TAction> Create(
IProblem <TState, TAction> problem,
ValueTable <TState, TAction> valueTable,
IRewarder <TState, TAction> rewarder)
{
var greedyPolicy = new GreedyPolicy <TState, TAction>(problem);
foreach (var state in problem.AllStates())
{
var bestAction = FindBestAction(problem, state, valueTable, rewarder);
greedyPolicy._actions[state] = bestAction;
}
return(greedyPolicy);
}
private static bool AllValuesAreEqual(
IProblem <GamblersWorldState, GamblersWorldAction> problem,
ValueTable <GamblersWorldState, GamblersWorldAction> genericValues,
GamblersValueTable gamblersValues)
{
foreach (var state in problem.AllStates())
{
var genericValue = genericValues.Value(state);
var gamblerValue = gamblersValues.Value(state);
Assert.AreEqual(genericValue, gamblerValue, 0.01,
$"values not equal for state {state}. " +
$"generic: {genericValue}, gambler: {gamblerValue}");
}
return(true);
}
private static bool AllValuesAreEqual(
IProblem <GridWorldState, GridWorldAction> problem,
ValueTable <GridWorldState, GridWorldAction> genericValues,
GridWorldValueTable gridValues)
{
foreach (var state in problem.AllStates())
{
var genericValue = genericValues.Value(state);
var gridValue = gridValues.Value(state);
Console.WriteLine($"generic: {genericValue}, grid {gridValue}");
// Assert.AreEqual(genericValue, gridValue, 0.01,
// $"values not equal for state {state}. " +
// $"generic: {genericValue}, grid: {gridValue}");
}
return(true);
}
public ValueTable(IProblem <TState, TAction> problem)
{
_problem = problem;
_values = problem.AllStates().ToDictionary(s => s, s => 0.0);
}