Changeset 12893 for branches/HeuristicLab.Problems.GrammaticalOptimization-gkr/HeuristicLab.Algorithms.Bandits/Policies/ChernoffIntervalEstimationPolicy.cs

Timestamp:

08/24/15 13:56:27 (9 years ago)

Author:

gkronber

Message:

#2283: experiments on grammatical optimization algorithms (maxreward instead of avg reward, ...)

File:

• branches/HeuristicLab.Problems.GrammaticalOptimization-gkr/HeuristicLab.Algorithms.Bandits/Policies/ChernoffIntervalEstimationPolicy.cs (modified) (1 diff)

branches/HeuristicLab.Problems.GrammaticalOptimization-gkr/HeuristicLab.Algorithms.Bandits/Policies/ChernoffIntervalEstimationPolicy.cs

@@ -33 +33 @@
         } else {
 
-          var avgReward = aInfo.SumReward / aInfo.Tries;
+          var avgReward = aInfo.SumReward / aInfo.Tries;          
 
           // page 5 of "A simple distribution-free approach to the max k-armed bandit problem"