|
QLearningUpdateState Method
|
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 action,
double reward,
int nextState
)
Public Sub UpdateState (
previousState As Integer,
action As Integer,
reward As Double,
nextState As Integer
)
Request Example
View SourceParameters
- previousState
- Type: SystemInt32
Previous state. - action
- Type: SystemInt32
Action, which leads from previous to the next state. - reward
- Type: SystemDouble
Reward value, received by taking specified action from previous state. - nextState
- Type: SystemInt32
Next state.
See Also