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 EndToEndEpsilonGreedy()
{
uint numActions = 10;
float epsilon = 0.5f;
TestRecorder <SimpleContext> recorder = new TestRecorder <SimpleContext>();
MwtExplorer <SimpleContext> mwtt = new MwtExplorer <SimpleContext>("mwt", recorder);
TestSimplePolicy policy = new TestSimplePolicy();
var explorer = new EpsilonGreedyExplorer <SimpleContext>(policy, epsilon, numActions);
EndToEnd(mwtt, explorer, recorder);
}
public void EndToEndBagging()
{
uint numActions = 10;
uint numbags = 2;
TestRecorder <SimpleContext> recorder = new TestRecorder <SimpleContext>();
TestSimplePolicy[] policies = new TestSimplePolicy[numbags];
for (int i = 0; i < numbags; i++)
{
policies[i] = new TestSimplePolicy();
}
MwtExplorer <SimpleContext> mwtt = new MwtExplorer <SimpleContext>("mwt", recorder);
var explorer = new BaggingExplorer <SimpleContext>(policies, numbags, numActions);
EndToEnd(mwtt, explorer, recorder);
}