Changeset 11742 for branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Problems.GrammaticalOptimization.Test/TestBanditPolicies.cs

Timestamp:

01/09/15 14:57:28 (9 years ago)

Author:

gkronber

Message:

#2283 refactoring

File:

• branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Problems.GrammaticalOptimization.Test/TestBanditPolicies.cs (modified) (6 diffs)

branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Problems.GrammaticalOptimization.Test/TestBanditPolicies.cs

@@ -4 +4 @@
 using System.Globalization;
 using HeuristicLab.Algorithms.Bandits;
+using HeuristicLab.Algorithms.Bandits.BanditPolicies;
 using HeuristicLab.Algorithms.Bandits.Models;
 using Microsoft.VisualStudio.TestTools.UnitTesting;
@@ -16 +17 @@
       var nArms = 20;
 
-      // Console.WriteLine("Threshold Ascent (20)"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new ThresholdAscent(20, 0.01));
-      // Console.WriteLine("Threshold Ascent (100)"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new ThresholdAscent(100, 0.01));
-      // Console.WriteLine("Threshold Ascent (500)"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new ThresholdAscent(500, 0.01));
-      // Console.WriteLine("Threshold Ascent (1000)"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new ThresholdAscent(1000, 0.01));
-      Console.WriteLine("Thompson (Gaussian fixed variance)"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0, 1, 1)));
-      Console.WriteLine("Thompson (Gaussian est variance)"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0, 1, 1, 0.1)));
+      // ThresholdAscent only works for rewards in [0..1] so far
+
+      Console.WriteLine("Thompson (Gaussian est variance)"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0, 1, 1, 1)));
+      Console.WriteLine("Thompson (Gaussian fixed variance)"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0, 1, 0.1)));
       Console.WriteLine("GaussianThompson (compat)"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new GaussianThompsonSamplingPolicy(true));
       Console.WriteLine("GaussianThompson"); TestPolicyGaussianUnknownVariance(randSeed, nArms, new GaussianThompsonSamplingPolicy());
@@ -91 +90 @@
       var randSeed = 31415;
       var nArms = 20;
+      Console.WriteLine("Threshold Ascent (20)"); TestPolicyGaussian(randSeed, nArms, new ThresholdAscentPolicy(20, 0.01));
+      Console.WriteLine("Threshold Ascent (100)"); TestPolicyGaussian(randSeed, nArms, new ThresholdAscentPolicy(100, 0.01));
+      Console.WriteLine("Threshold Ascent (500)"); TestPolicyGaussian(randSeed, nArms, new ThresholdAscentPolicy(500, 0.01));
+      Console.WriteLine("Threshold Ascent (1000)"); TestPolicyGaussian(randSeed, nArms, new ThresholdAscentPolicy(1000, 0.01));
+      Console.WriteLine("Generic Thompson (Gaussian fixed var)"); TestPolicyGaussian(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0.5, 1)));
+      Console.WriteLine("Generic Thompson (Gaussian unknown var)"); TestPolicyGaussian(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0.5, 1, 1, 1)));
       Console.WriteLine("Thompson (Gaussian orig)"); TestPolicyGaussian(randSeed, nArms, new GaussianThompsonSamplingPolicy(true));
       Console.WriteLine("Thompson (Gaussian new)"); TestPolicyGaussian(randSeed, nArms, new GaussianThompsonSamplingPolicy());
-      Console.WriteLine("Generic Thompson (Gaussian)"); TestPolicyGaussian(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0.5, 1)));
+
       /*
       Console.WriteLine("Random"); TestPolicyNormal(randSeed, nArms, new RandomPolicy(new Random(seedForPolicy), nArms));
@@ -123 +128 @@
       Console.WriteLine("ChernoffIntervalEstimationPolicy(0.01)"); TestPolicyNormal(randSeed, nArms, new ChernoffIntervalEstimationPolicy(nArms, 0.01));
       Console.WriteLine("ChernoffIntervalEstimationPolicy(0.05)"); TestPolicyNormal(randSeed, nArms, new ChernoffIntervalEstimationPolicy(nArms, 0.05));
-      Console.WriteLine("ChernoffIntervalEstimationPolicy(0.1) "); TestPolicyNormal(randSeed, nArms, new ChernoffIntervalEstimationPolicy(nArms, 0.1));
+      Console.WriteLine("ChernoffIntervalEstimationPolicy(0.1) "); TestPolicyNormal(randSeed, nArms, new ChernoffIntervalEstimationPolicy(nArms, 0.1));      
       Console.WriteLine("ThresholdAscent(10,0.01)  "); TestPolicyNormal(randSeed, nArms, new ThresholdAscentPolicy(nArms, 10, 0.01));
       Console.WriteLine("ThresholdAscent(10,0.05)  "); TestPolicyNormal(randSeed, nArms, new ThresholdAscentPolicy(nArms, 10, 0.05));
@@ -141 +146 @@
       var randSeed = 31415;
       var nArms = 20;
+      Console.WriteLine("Threshold Ascent (20)"); TestPolicyGaussianMixture(randSeed, nArms, new ThresholdAscentPolicy(20, 0.01));
+      Console.WriteLine("Threshold Ascent (100)"); TestPolicyGaussianMixture(randSeed, nArms, new ThresholdAscentPolicy(100, 0.01));
+      Console.WriteLine("Threshold Ascent (500)"); TestPolicyGaussianMixture(randSeed, nArms, new ThresholdAscentPolicy(500, 0.01));
+      Console.WriteLine("Threshold Ascent (1000)"); TestPolicyGaussianMixture(randSeed, nArms, new ThresholdAscentPolicy(1000, 0.01));
       Console.WriteLine("Thompson (Gaussian orig)"); TestPolicyGaussianMixture(randSeed, nArms, new GaussianThompsonSamplingPolicy(true));
       Console.WriteLine("Thompson (Gaussian new)"); TestPolicyGaussianMixture(randSeed, nArms, new GaussianThompsonSamplingPolicy());
-      Console.WriteLine("Generic Thompson (Gaussian)"); TestPolicyGaussianMixture(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0.5, 1)));
+      Console.WriteLine("Generic Thompson (Gaussian fixed variance)"); TestPolicyGaussianMixture(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0.5, 1, 0.1)));
+      Console.WriteLine("Generic Thompson (Gaussian unknown variance)"); TestPolicyGaussianMixture(randSeed, nArms, new GenericThompsonSamplingPolicy(new GaussianModel(0.5, 1, 1, 1)));
 
       /*
@@ -167 +177 @@
 
 
-    private void TestPolicyBernoulli(int randSeed, int nArms, IPolicy policy) {
+    private void TestPolicyBernoulli(int randSeed, int nArms, IBanditPolicy policy) {
       TestPolicy(randSeed, nArms, policy, (banditRandom, nActions) => new BernoulliBandit(banditRandom, nActions));
     }
-    private void TestPolicyGaussian(int randSeed, int nArms, IPolicy policy) {
+    private void TestPolicyGaussian(int randSeed, int nArms, IBanditPolicy policy) {
       TestPolicy(randSeed, nArms, policy, (banditRandom, nActions) => new TruncatedNormalBandit(banditRandom, nActions));
     }
-    private void TestPolicyGaussianMixture(int randSeed, int nArms, IPolicy policy) {
+    private void TestPolicyGaussianMixture(int randSeed, int nArms, IBanditPolicy policy) {
       TestPolicy(randSeed, nArms, policy, (banditRandom, nActions) => new GaussianMixtureBandit(banditRandom, nActions));
     }
-    private void TestPolicyGaussianUnknownVariance(int randSeed, int nArms, IPolicy policy) {
+    private void TestPolicyGaussianUnknownVariance(int randSeed, int nArms, IBanditPolicy policy) {
       TestPolicy(randSeed, nArms, policy, (banditRandom, nActions) => new GaussianBandit(banditRandom, nActions));
     }
 
 
-    private void TestPolicy(int randSeed, int nArms, IPolicy policy, Func<Random, int, IBandit> banditFactory) {
+    private void TestPolicy(int randSeed, int nArms, IBanditPolicy policy, Func<Random, int, IBandit> banditFactory) {
       var maxIt = 1E5;
       var reps = 10; // independent runs