Predict.Neural.Network.A3C: Predict Neural Network

In MartinKies/USLR: Reinforcement Learning with R

Description

Predict action probabilities and state values based on a neural network.

Usage

Predict.Neural.Network.A3C(model, model.par, state, Indicator = NULL)

Arguments

model	A Neural Network e.g. as given by Setup.Neural.Network.A3c or Setup.Neural.Network.A3c.LSTM.
model.par	A list with parameters to set up the Network e.g. as given by Get.Def.Par.Neural.Network.A3C or Get.Def.Par.Neural.Network.A3C.LSTM.
state	An encoded game state.
Indicator	Indicates which value should be returned. Could be either: "Value" Only the predicted value of the state is returned. "Prob" Only the action probabilites of the given state are returned. NULL Both are retured.

MartinKies/USLR documentation built on Nov. 10, 2019, 5:24 a.m.