private void Step <TOutcome>(RunContext runContext, IOutcomeReporter <TOutcome> outcomeReporter, IStepContext <TOutcome> step)
{
string eventId = step.EventId;
if (!liveModel.TryChooseRank(eventId, step.DecisionContext, runContext.ResponseContainer, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
long actionIndex = -1;
if (!runContext.ResponseContainer.TryGetChosenAction(out actionIndex, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
TOutcome outcome = step.GetOutcome(actionIndex, runContext.ResponseContainer.AsEnumerable());
if (outcome == null)
{
return;
}
if (!outcomeReporter.TryQueueOutcomeEvent(runContext, eventId, outcome))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
}
private void Step <TOutcome>(RunContext runContext, IOutcomeReporter <TOutcome> outcomeReporter, IStepContext <TOutcome> step)
{
string eventId = step.EventId;
TOutcome outcome = default(TOutcome);
if (loopKind == LoopKind.Slates)
{
if (!liveModel.TryRequestMultiSlotDecision(eventId, step.SlatesContext, runContext.SlatesContainer, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
int[] actions = runContext.SlatesContainer.Select(slot => slot.ActionId).ToArray();
float[] probs = runContext.SlatesContainer.Select(slot => slot.Probability).ToArray();
outcome = step.GetSlatesOutcome(actions, probs);
if (outcome == null)
{
return;
}
}
else if (loopKind == LoopKind.CA)
{
if (!liveModel.TryRequestContinuousAction(eventId, step.ContinuousActionContext, runContext.ContinuousActionContainer, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
float action = runContext.ContinuousActionContainer.ChosenAction;
float pdfValue = runContext.ContinuousActionContainer.ChosenActionPdfValue;
outcome = step.GetContinuousActionOutcome(action, pdfValue);
if (outcome == null)
{
return;
}
}
else
{
if (!liveModel.TryChooseRank(eventId, step.DecisionContext, runContext.ResponseContainer, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
long actionIndex = -1;
if (!runContext.ResponseContainer.TryGetChosenAction(out actionIndex, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
outcome = step.GetOutcome(actionIndex, runContext.ResponseContainer.AsEnumerable());
if (outcome == null)
{
return;
}
}
if (!outcomeReporter.TryQueueOutcomeEvent(runContext, eventId, outcome))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
}
public void Test_DeserializeReplayStep_WithoutObservation()
{
// Arrange
string expectedEventId = "my_experiment-t1-n10-f2-a4-0-0";
string expectedContext = PrepareJson("{ \"GUser\":{\"f_int\":0,\"f_float\":0.5,\"f_str_0\":\"value_0\",\"f_str_1\":\"value_1\"}, \"_multi\": [ { \"TAction\":{\"a_f_0\":\"value_0\",\"a_f_1\":\"value_1\"}},{ \"TAction\":{\"a_f_0\":\"value_1\",\"a_f_1\":\"value_2\"}},{ \"TAction\":{\"a_f_0\":\"value_2\",\"a_f_1\":\"value_3\"}},{ \"TAction\":{\"a_f_0\":\"value_3\",\"a_f_1\":\"value_4\"}}] }");
string expectedObservation = null;
const string dsJsonWithObservation = "{\"_label_cost\":-0,\"_label_probability\":0.25,\"_label_Action\":1,\"_labelIndex\":0,\"Version\":\"1\",\"EventId\":\"my_experiment-t1-n10-f2-a4-0-0\",\"a\":[1,2,3,4],\"c\":{ \"GUser\":{\"f_int\":0,\"f_float\":0.5,\"f_str_0\":\"value_0\",\"f_str_1\":\"value_1\"}, \"_multi\": [ { \"TAction\":{\"a_f_0\":\"value_0\",\"a_f_1\":\"value_1\"}},{ \"TAction\":{\"a_f_0\":\"value_1\",\"a_f_1\":\"value_2\"}},{ \"TAction\":{\"a_f_0\":\"value_2\",\"a_f_1\":\"value_3\"}},{ \"TAction\":{\"a_f_0\":\"value_3\",\"a_f_1\":\"value_4\"}}] },\"p\":[0.250000,0.250000,0.250000,0.250000],\"VWState\":{\"m\":\"N/A\"}}";
// Act
IStepContext <string> stepContext = ReplayStepProvider.DeserializeReplayStep(dsJsonWithObservation);
string actualObservation = stepContext.GetOutcome(0, new ActionProbability[0]);
Assert.AreEqual(expectedEventId, stepContext.EventId, $"{nameof(stepContext.EventId)} is not properly deserialized.");
Assert.AreEqual(expectedContext, stepContext.DecisionContext, $"{nameof(stepContext.DecisionContext)} is not properly deserialized.");
Assert.AreEqual(expectedObservation, actualObservation, $"Observation is not properly deserialized.");
}
private void Step <TOutcome>(RunContext runContext, IOutcomeReporter <TOutcome> outcomeReporter, IStepContext <TOutcome> step)
{
string eventId = step.EventId;
TOutcome outcome = default(TOutcome);
if (loopKind == LoopKind.Slates)
{
if (!liveModel.TryRequestMultiSlotDecision(eventId, step.SlatesContext, runContext.MultiSlotResponseContainer, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
int[] actions = runContext.MultiSlotResponseContainer.Select(slot => slot.ActionId).ToArray();
float[] probs = runContext.MultiSlotResponseContainer.Select(slot => slot.Probability).ToArray();
outcome = step.GetSlatesOutcome(actions, probs);
if (outcome == null)
{
return;
}
}
else if (loopKind == LoopKind.CA)
{
if (!liveModel.TryRequestContinuousAction(eventId, step.ContinuousActionContext, runContext.ContinuousActionContainer, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
float action = runContext.ContinuousActionContainer.ChosenAction;
float pdfValue = runContext.ContinuousActionContainer.ChosenActionPdfValue;
outcome = step.GetContinuousActionOutcome(action, pdfValue);
if (outcome == null)
{
return;
}
}
else if (loopKind == LoopKind.CCB)
{
if (!liveModel.TryRequestDecision(step.DecisionContext, runContext.DecisionResponseContainer, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
// TODO: Populate actionProbs. Currently GetOutcome() just returns a fixed outcome value, so the values of actionProbs don't matter.
ActionProbability[] actionProbs = new ActionProbability[runContext.DecisionResponseContainer.Count];
foreach (var slot in runContext.DecisionResponseContainer)
{
outcome = step.GetOutcome(slot.ActionId, actionProbs);
if (!outcomeReporter.TryQueueOutcomeEvent(runContext, slot.SlotId, outcome))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
}
return;
}
else if (loopKind == LoopKind.CCBv2)
{
if (!liveModel.TryRequestMultiSlotDecisionDetailed(eventId, step.DecisionContext, runContext.MultiSlotResponseDetailedContainer, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
foreach (var slot in runContext.MultiSlotResponseDetailedContainer)
{
outcome = step.GetOutcome(slot.ChosenAction, slot);
if (!outcomeReporter.TryQueueOutcomeEvent(runContext, eventId, slot.SlotId, outcome))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
}
return;
}
else
{
if (!liveModel.TryChooseRank(eventId, step.DecisionContext, runContext.ResponseContainer, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
long actionIndex = -1;
if (!runContext.ResponseContainer.TryGetChosenAction(out actionIndex, runContext.ApiStatusContainer))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
outcome = step.GetOutcome(actionIndex, runContext.ResponseContainer.AsEnumerable());
if (outcome == null)
{
return;
}
}
if (!outcomeReporter.TryQueueOutcomeEvent(runContext, eventId, outcome))
{
this.SafeRaiseError(runContext.ApiStatusContainer);
}
}