Initializes a new instance of the QLearning class.
Namespace:
AForge.MachineLearningAssembly: AForge.MachineLearning (in AForge.MachineLearning.dll) Version: 2.2.4.0 (2.2.4.0)
Syntax
C# |
---|
public QLearning( int states, int actions, IExplorationPolicy explorationPolicy, bool randomize ) |
Parameters
- states
- Type: System..::.Int32
Amount of possible states.
- actions
- Type: System..::.Int32
Amount of possible actions.
- explorationPolicy
- Type: AForge.MachineLearning..::.IExplorationPolicy
Exploration policy.
- randomize
- Type: System..::.Boolean
Randomize action estimates or not.
Remarks
The randomize parameter specifies if initial action estimates should be randomized
with small values or not. Randomization of action values may be useful, when greedy exploration
policies are used. In this case randomization ensures that actions of the same type are not chosen always.