DataPredict

API Reference - Models - DeepDoubleExpectedStateActionRewardStateActionV1 (Double Deep Expected SARSA)

DeepDoubleExpectedStateActionRewardStateActionV1 is a neural network with reinforcement learning capabilities. It can predict any positive numbers of discrete values.

Stored Model Parameters

Contains a table of matrices.

Constructors

new()

Create new model object. If any of the arguments are nil, default argument values for that argument will be used.

DeepDoubleExpectedStateActionRewardStateAction.new(epsilon: number, discountFactor: number): ModelObject

Parameters:

Returns:

Functions

setParameters()

Set model’s parameters. When any of the arguments are nil, previous argument values for that argument will be used.

DeepDoubleExpectedStateActionRewardStateAction:setParameters(epsilon: number, discountFactor: number)

Parameters:

setModelParameters1()

Sets model parameters to be used by the model.

DeepDoubleExpectedStateActionRewardStateAction:setModelParameters1(ModelParameters1: ModelParameters)

Parameters:

setModelParameters2()

Sets model parameters to be used by the model.

DeepDoubleExpectedStateActionRewardStateAction:setModelParameters1(ModelParameters2: ModelParameters)

Parameters:

setModelParameters1()

Sets model parameters to be used by the model.

DeepDoubleExpectedStateActionRewardStateAction:setModelParameters1(ModelParameters1: ModelParameters, doNotDeepCopy: boolean)

Parameters:

setModelParameters2()

Sets model parameters to be used by the model.

DeepDoubleExpectedStateActionRewardStateAction:setModelParameters2(ModelParameters2: ModelParameters, doNotDeepCopy: boolean)

Parameters:

getModelParameters1()

Sets model parameters to be used by the model.

DeepDoubleExpectedStateActionRewardStateAction:getModelParameters1(doNotDeepCopy: boolean): ModelParameters

Parameters:

Returns:

getModelParameters2()

Sets model parameters to be used by the model.

DeepDoubleExpectedStateActionRewardStateAction:getModelParameters2(doNotDeepCopy: boolean): ModelParameters

Parameters:

Returns:

Inherited From

References