DeepDoubleExpectedStateActionRewardStateActionV1 is a neural network with reinforcement learning capabilities. It can predict any positive numbers of discrete values.
Contains a table of matrices.
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
epsilon: Controls the balance between exploration and exploitation for calculating expected Q-values. The value must be set between 0 and 1. The value 0 focuses on exploitation only and 1 focuses on exploration only.
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.
DeepDoubleExpectedStateActionRewardStateAction:setParameters(epsilon: number, discountFactor: number)
epsilon: Controls the balance between exploration and exploitation for calculating expected Q-values. The value must be set between 0 and 1. The value 0 focuses on exploitation only and 1 focuses on exploration only.
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.
DeepDoubleExpectedStateActionRewardStateAction:setModelParameters1(ModelParameters1: ModelParameters)
Sets model parameters to be used by the model.
DeepDoubleExpectedStateActionRewardStateAction:setModelParameters1(ModelParameters2: ModelParameters)
Sets model parameters to be used by the model.
DeepDoubleExpectedStateActionRewardStateAction:setModelParameters1(ModelParameters1: ModelParameters, doNotDeepCopy: boolean)
ModelParameters1: First model parameters to be used by the model.
doNotDeepCopy: Set whether or not to deep copy the model parameters.
Sets model parameters to be used by the model.
DeepDoubleExpectedStateActionRewardStateAction:setModelParameters2(ModelParameters2: ModelParameters, doNotDeepCopy: boolean)
ModelParameters2: Second model parameters to be used by the model.
doNotDeepCopy: Set whether or not to deep copy the model parameters.
Sets model parameters to be used by the model.
DeepDoubleExpectedStateActionRewardStateAction:getModelParameters1(doNotDeepCopy: boolean): ModelParameters
Sets model parameters to be used by the model.
DeepDoubleExpectedStateActionRewardStateAction:getModelParameters2(doNotDeepCopy: boolean): ModelParameters