Changeset 11747 for branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Algorithms.Bandits/BanditPolicies/MeanAndVariancePolicyActionInfo.cs

Timestamp:

01/12/15 21:23:01 (9 years ago)

Author:

gkronber

Message:

#2283: implemented test problems for MCTS

File:

• branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Algorithms.Bandits/BanditPolicies/MeanAndVariancePolicyActionInfo.cs (modified) (2 diffs)

branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Algorithms.Bandits/BanditPolicies/MeanAndVariancePolicyActionInfo.cs

@@ -11 +11 @@
     public bool Disabled { get { return disabled; } }
     private OnlineMeanAndVarianceEstimator estimator = new OnlineMeanAndVarianceEstimator();
+    private double knownValue;
     public int Tries { get { return estimator.N; } }
     public double SumReward { get { return estimator.Sum; } }
     public double AvgReward { get { return estimator.Avg; } }
     public double RewardVariance { get { return estimator.Variance; } }
-    public double Value { get { return AvgReward; } }
+    public double Value {
+      get {
+        if (disabled) return knownValue;
+        else
+          return AvgReward;
+      }
+    }
 
     public void UpdateReward(double reward) {
@@ -22 +29 @@
     }
 
-    public void Disable() {
+    public void Disable(double reward) {
       disabled = true;
+      this.knownValue = reward;
     }
 
     public void Reset() {
       disabled = false;
+      knownValue = 0.0;
       estimator.Reset();
     }