Update Q-function's value for the previous state-action pair.
Namespace:
AForge.MachineLearningAssembly: AForge.MachineLearning (in AForge.MachineLearning.dll) Version: 2.2.4.0 (2.2.4.0)
Syntax
C# |
---|
public void UpdateState( int previousState, int previousAction, double reward, int nextState, int nextAction ) |
Parameters
- previousState
- Type: System..::.Int32
Curren state.
- previousAction
- Type: System..::.Int32
Action, which lead from previous to the next state.
- reward
- Type: System..::.Double
Reward value, received by taking specified action from previous state.
- nextState
- Type: System..::.Int32
Next state.
- nextAction
- Type: System..::.Int32
Next action.
Remarks
Updates Q-function's value for the previous state-action pair in
the case if the next state is non terminal.