DataPredict

API Reference - Models - DeepClippedDoubleQLearning (Clipped Double Deep Q-Learning)

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

It uses two neural networks where lowest maximum Q-values are selected for training.

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

DeepClippedDoubleQLearning.new(discountFactor: number): ModelObject

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

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

DeepClippedDoubleQLearning:setParameters(discountFactor: number)

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

Sets model parameters to be used by the model.

DeepClippedDoubleQLearning:setModelParameters1(ModelParameters1: ModelParameters)

Sets model parameters to be used by the model.

DeepClippedDoubleQLearning:setModelParameters1(ModelParameters2: ModelParameters)

Sets model parameters to be used by the model.

DeepClippedDoubleQLearning:getModelParameters1(): ModelParameters

Sets model parameters to be used by the model.

DeepClippedDoubleQLearning:getModelParameters2(): ModelParameters