Training the network

Before training the network, we must split the data. We will start with data splitting, subdividing data into exactly two subsets of a specified ratio for training and validation. This technique is particularly useful when you have a very large dataset. In this case, the dataset is divided into two partitions: training and test. The training set is used to train the model, while the test set will provide us with a significant performance estimate. This method is very advantageous when using slow methods and needing a quick approximation of performance.

The following example divides the dataset so that 70 percent is used to train a neural network model and the remaining 30 percent is used to evaluate model performance: ...

Get Hands-On Reinforcement Learning with R now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.