QLearning Constructor (Int32, Int32, IExplorationPolicy, Boolean)

Initializes a new instance of the QLearning class.

Namespace: Accord.MachineLearning
Assembly: Accord.MachineLearning (in Accord.MachineLearning.dll) Version: 3.8.0

Syntax

Copy

public QLearning(
	int states,
	int actions,
	IExplorationPolicy explorationPolicy,
	bool randomize
)

Public Sub New ( 
	states As Integer,
	actions As Integer,
	explorationPolicy As IExplorationPolicy,
	randomize As Boolean
)

Request Example View Source

Parameters

states: Type: SystemInt32
Amount of possible states.
actions: Type: SystemInt32
Amount of possible actions.
explorationPolicy: Type: Accord.MachineLearningIExplorationPolicy
Exploration policy.
randomize: Type: SystemBoolean
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.

Reference

QLearning Class

QLearning Overload

Accord.MachineLearning Namespace