|
SarsaUpdateState Method (Int32, Int32, Double, Int32, Int32)
|
Update Q-function's value for the previous state-action pair.
Namespace:
Accord.MachineLearning
Assembly:
Accord.MachineLearning (in Accord.MachineLearning.dll) Version: 3.8.0
Syntax public void UpdateState(
int previousState,
int previousAction,
double reward,
int nextState,
int nextAction
)
Public Sub UpdateState (
previousState As Integer,
previousAction As Integer,
reward As Double,
nextState As Integer,
nextAction As Integer
)
Request Example
View SourceParameters
- previousState
- Type: SystemInt32
Curren state. - previousAction
- Type: SystemInt32
Action, which lead from previous to the next state. - reward
- Type: SystemDouble
Reward value, received by taking specified action from previous state. - nextState
- Type: SystemInt32
Next state. - nextAction
- Type: SystemInt32
Next action.
Remarks Updates Q-function's value for the previous state-action pair in
the case if the next state is non terminal.
See Also