DataPredict

API Reference - Models - DeepStateActionRewardStateAction (Deep SARSA)

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

Constructors

new()

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

DeepStateActionRewardStateAction.new(discountFactor: number): ModelObject

Parameters:

• discountFactor: The higher the value, the more likely it focuses on long-term outcomes. The value must be set between 0 and 1.

Returns:

• ModelObject: The generated model object.

Functions

setParameters()

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

DeepStateActionRewardStateAction:setParameters(discountFactor: number)

Parameters:

• discountFactor: The higher the value, the more likely it focuses on long-term outcomes. The value must be set between 0 and 1.

Inherited From

• ReinforcementLearningBaseModel

References

• SARSA Reinforcement Learning

• Reinforcement Learning with Neural Network