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

Timestamp:

01/12/15 21:23:01 (10 years ago)

Author:

gkronber

Message:

#2283: implemented test problems for MCTS

File:

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

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

@@ -10 +10 @@
   public class ModelPolicyActionInfo : IBanditPolicyActionInfo {
     private readonly IModel model;
+    private double knownValue;
     public bool Disabled { get { return Tries == -1; } }
-    public double Value { get { return model.SampleExpectedReward(new Random()); } }
+    public double Value {
+      get {
+        if (Disabled) return knownValue;
+        else
+          return model.SampleExpectedReward(new Random());
+      }
+    }
 
     public int Tries { get; private set; }
@@ -28 +35 @@
     }
 
-    public void Disable() {
+    public void Disable(double reward) {
       this.Tries = -1;
+      this.knownValue = reward;
     }
 
     public void Reset() {
       Tries = 0;
+      knownValue = 0.0;
       model.Reset();
     }