Changeset 11806 for branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Algorithms.Bandits/BanditPolicies/UCB1Policy.cs
- Timestamp:
- 01/20/15 20:25:00 (9 years ago)
- File:
-
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
branches/HeuristicLab.Problems.GrammaticalOptimization/HeuristicLab.Algorithms.Bandits/BanditPolicies/UCB1Policy.cs
r11747 r11806 13 13 var myActionInfos = actionInfos.OfType<DefaultPolicyActionInfo>(); 14 14 double bestQ = double.NegativeInfinity; 15 int totalTries = myActionInfos. Where(a => !a.Disabled).Sum(a => a.Tries);15 int totalTries = myActionInfos.Sum(a => a.Tries); 16 16 17 17 var bestActions = new List<int>(); … … 19 19 foreach (var aInfo in myActionInfos) { 20 20 aIdx++; 21 if (aInfo.Disabled) continue;22 21 double q; 23 22 if (aInfo.Tries == 0) { … … 31 30 bestActions.Clear(); 32 31 bestActions.Add(aIdx); 33 } else if (q == bestQ) {32 } else if (q.IsAlmost(bestQ)) { 34 33 bestActions.Add(aIdx); 35 34 }
Note: See TracChangeset
for help on using the changeset viewer.