Changeset 12893 for branches/HeuristicLab.Problems.GrammaticalOptimization-gkr/HeuristicLab.Algorithms.GrammaticalOptimization/ISequentialDecisionPolicy.cs
- Timestamp:
- 08/24/15 13:56:27 (9 years ago)
- File:
-
- 1 edited
Legend:
- Unmodified
- Added
- Removed
-
branches/HeuristicLab.Problems.GrammaticalOptimization-gkr/HeuristicLab.Algorithms.GrammaticalOptimization/ISequentialDecisionPolicy.cs
r11850 r12893 12 12 // we also assume that the policy can fail to select one of the followStates 13 13 public interface ISequentialDecisionPolicy<in TState> { 14 bool TrySelect( Random random, TState curState, IEnumerable<TState> afterStates, out int selectedStateIdx); // selectedState \in afterStates14 bool TrySelect(System.Random random, TState curState, IEnumerable<TState> afterStates, out int selectedStateIdx); // selectedState \in afterStates 15 15 16 16 // state-trajectory are the states of the episode, at the end we recieved the reward (only for the terminal state)
Note: See TracChangeset
for help on using the changeset viewer.