public void UsageBadVariableActionContext()
{
int numExceptionsCaught = 0;
int numExceptionsExpected = 5;
var tryCatchArgumentException = (Action <Action>)((action) => {
try
{
action();
}
catch (ArgumentException ex)
{
if (ex.ParamName.ToLower() == "ctx")
{
numExceptionsCaught++;
}
}
});
tryCatchArgumentException(() => {
var mwt = new MwtExplorer <TestContext>("test", new TestRecorder <TestContext>());
var policy = new TestPolicy <TestContext>();
var explorer = new EpsilonGreedyExplorer <TestContext>(policy, 0.2f);
mwt.ChooseAction(explorer, "key", new TestContext());
});
tryCatchArgumentException(() =>
{
var mwt = new MwtExplorer <TestContext>("test", new TestRecorder <TestContext>());
var policy = new TestPolicy <TestContext>();
var explorer = new TauFirstExplorer <TestContext>(policy, 10);
mwt.ChooseAction(explorer, "key", new TestContext());
});
tryCatchArgumentException(() =>
{
var mwt = new MwtExplorer <TestContext>("test", new TestRecorder <TestContext>());
var policies = new TestPolicy <TestContext> [2];
for (int i = 0; i < 2; i++)
{
policies[i] = new TestPolicy <TestContext>(i * 2);
}
var explorer = new BootstrapExplorer <TestContext>(policies);
mwt.ChooseAction(explorer, "key", new TestContext());
});
tryCatchArgumentException(() =>
{
var mwt = new MwtExplorer <TestContext>("test", new TestRecorder <TestContext>());
var scorer = new TestScorer <TestContext>(10);
var explorer = new SoftmaxExplorer <TestContext>(scorer, 0.5f);
mwt.ChooseAction(explorer, "key", new TestContext());
});
tryCatchArgumentException(() =>
{
var mwt = new MwtExplorer <TestContext>("test", new TestRecorder <TestContext>());
var scorer = new TestScorer <TestContext>(10);
var explorer = new GenericExplorer <TestContext>(scorer);
mwt.ChooseAction(explorer, "key", new TestContext());
});
Assert.AreEqual(numExceptionsExpected, numExceptionsCaught);
}
public void TauFirst()
{
uint numActions = 10;
uint tau = 0;
string uniqueKey = "ManagedTestId";
TestRecorder <TestContext> recorder = new TestRecorder <TestContext>();
TestPolicy policy = new TestPolicy();
MwtExplorer <TestContext> mwtt = new MwtExplorer <TestContext>("mwt", recorder);
TestContext testContext = new TestContext()
{
Id = 100
};
var explorer = new TauFirstExplorer <TestContext>(policy, tau, numActions);
uint expectedAction = policy.ChooseAction(testContext);
uint chosenAction = mwtt.ChooseAction(explorer, uniqueKey, testContext);
Assert.AreEqual(expectedAction, chosenAction);
var interactions = recorder.GetAllInteractions();
Assert.AreEqual(0, interactions.Count);
}
public void TauFirstFixedActionUsingVariableActionInterface()
{
int numActions = 10;
int tau = 0;
var testContext = new VariableActionTestContext(numActions)
{
Id = 100
};
var policy = new TestPolicy <VariableActionTestContext>();
var explorer = new TauFirstExplorer(tau);
TauFirstWithContext(numActions, testContext, policy, explorer);
}
public void TauFirst()
{
int numActions = 10;
int tau = 0;
RegularTestContext testContext = new RegularTestContext()
{
Id = 100
};
var policy = new TestPolicy <RegularTestContext>();
var explorer = new TauFirstExplorer(tau);
TauFirstWithContext(numActions, testContext, policy, explorer);
}
public void EndToEndTauFirst()
{
uint numActions = 10;
uint tau = 5;
TestRecorder <SimpleContext> recorder = new TestRecorder <SimpleContext>();
TestSimplePolicy policy = new TestSimplePolicy();
MwtExplorer <SimpleContext> mwtt = new MwtExplorer <SimpleContext>("mwt", recorder);
var explorer = new TauFirstExplorer <SimpleContext>(policy, tau, numActions);
EndToEnd(mwtt, explorer, recorder);
}
public void TauFirst()
{
uint numActions = 10;
uint tau = 0;
TestContext testContext = new TestContext()
{
Id = 100
};
var policy = new TestPolicy <TestContext>();
var explorer = new TauFirstExplorer <TestContext>(policy, tau, numActions);
TauFirstWithContext(numActions, testContext, policy, explorer);
}
static void ExploreTauFirst <TContext>
(
string appId,
int policyType,
JToken configPolicy,
int tau,
int numActions,
string[] experimentalUnitIdList,
TContext[] contextList,
string outputFile
)
{
var recorder = new StringRecorder <TContext>();
bool isVariableActionContext = typeof(IVariableActionContext).IsAssignableFrom(typeof(TContext));
switch (policyType)
{
case 0: // fixed policy
{
var policyAction = configPolicy["Action"].Value <uint>();
var policy = new TestPolicy <TContext> {
ActionToChoose = policyAction
};
var explorer = new TauFirstExplorer(tau);
var mwt = isVariableActionContext ?
MwtExplorer.Create(appId, new VariableActionProvider <TContext>(), recorder, explorer, policy) :
MwtExplorer.Create(appId, numActions, recorder, explorer, policy);
for (int i = 0; i < experimentalUnitIdList.Length; i++)
{
int numActionsVariable = isVariableActionContext ? ((IVariableActionContext)contextList[i]).GetNumberOfActions() : int.MaxValue;
mwt.ChooseAction(experimentalUnitIdList[i], contextList[i]);
}
File.AppendAllText(outputFile, recorder.GetRecording());
break;
}
}
}
