Train.Neural.Network: Train Neural Network

In MartinKies/USLR: Reinforcement Learning with R

Description

Trains a neural network and prints some helpful statistics. Returns a trained model.

Usage

Train.Neural.Network(model, model.par, x_train, y_train, action = NULL)

Arguments

model	A Neural Network e.g. given by Setup.Neural.Network
model.par	Parameters of Neural Network, e.g. given by Get.Default.Neural.Network
x_train	A Matrix with as much columns as input parameters in the encoding.
y_train	A Matrix with as much columns as output parameters (e.g. action parameters). For each state (x_train)/action combination(column of y_train) this value determines the target.
action	Which action has been taken to receive the respective reward?

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