DataPredict

API Reference - QuickSetups - DiagonalGaussianPolicy

DiagonalGaussianPolicy is a base class for setuping up reinforcement learning functions.

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

DiagonalGaussianPolicy.new(numberOfReinforcementsPerEpisode: integer): DiagonalGaussianPolicyObject

numberOfReinforcementsPerEpisode: The number of reinforcements to decay the epsilon value.

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

DiagonalGaussianPolicy:setParameters(numberOfReinforcementsPerEpisode: integer)

numberOfReinforcementsPerEpisode: The number of reinforcements to decay the epsilon value.

DiagonalGaussianPolicy:setModel(Model: ModelObject)

DiagonalGaussianPolicy:getModel(): ModelObject

Sets a new function on update alongside with the current model’s update() function.

DiagonalGaussianPolicy:extendUpdateFunction(updateFunction)

Sets a new function on episode update alongside with the current model’s episodeUpdate() function.

DiagonalGaussianPolicy:extendEpisodeUpdateFunction(episodeUpdateFunction)

episodeUpdateFunction: The function to run after calling the model’s episodeUpdate() function

Reward or punish model based on the current state of the environment.

DiagonalGaussianPolicy:reinforce(currentFeatureVector: matrix, actionStandardDeviationVector: matrix, rewardValue: number): matrix

currentFeatureVector: Matrix containing data from the current state.
actionStandardDeviationVector: The vector containing values of action’s standard deviations. The number of columns must match the number of actions.
rewardValue: The reward value added/subtracted from the current state (recommended value between -1 and 1, but can be larger than these values).

Resets the current parameters values.

DiagonalGaussianPolicy:reset()

Set whether or not to show the current number of episodes and current epsilon.

DiagonalGaussianPolicy:setPrintOutput(option: boolean)

option: A boolean value that determines the reinforcement output to be printed or not.

DiagonalGaussianPolicy:getCurrentNumberOfEpisodes(): integer

currentNumberOfEpisodes: The current number of episode stored inside the reinforcement learning quick setup object.

DiagonalGaussianPolicy:getCurrentNumberOfReinforcements(): integer

currentNumberOfReinforcements: The current number of times reinforce() has been called stored inside the reinforcement learning quick setup object.