Book Image

Advanced Deep Learning with TensorFlow 2 and Keras - Second Edition

By : Rowel Atienza
Book Image

Advanced Deep Learning with TensorFlow 2 and Keras - Second Edition

By: Rowel Atienza

Overview of this book

Advanced Deep Learning with TensorFlow 2 and Keras, Second Edition is a completely updated edition of the bestselling guide to the advanced deep learning techniques available today. Revised for TensorFlow 2.x, this edition introduces you to the practical side of deep learning with new chapters on unsupervised learning using mutual information, object detection (SSD), and semantic segmentation (FCN and PSPNet), further allowing you to create your own cutting-edge AI projects. Using Keras as an open-source deep learning library, the book features hands-on projects that show you how to create more effective AI with the most up-to-date techniques. Starting with an overview of multi-layer perceptrons (MLPs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs), the book then introduces more cutting-edge techniques as you explore deep neural network architectures, including ResNet and DenseNet, and how to create autoencoders. You will then learn about GANs, and how they can unlock new levels of AI performance. Next, you’ll discover how a variational autoencoder (VAE) is implemented, and how GANs and VAEs have the generative power to synthesize data that can be extremely convincing to humans. You'll also learn to implement DRL such as Deep Q-Learning and Policy Gradient Methods, which are critical to many modern results in AI.
Table of Contents (16 chapters)
14
Other Books You May Enjoy
15
Index

2. Monte Carlo policy gradient (REINFORCE) method

The simplest policy gradient method is REINFORCE [4], which is a Monte Carlo policy gradient method:

(Equation 10.2.1)

where Rt is the return as defined in Equation 9.1.2. Rt is an unbiased sample of in the policy gradient theorem.

Algorithm 10.2.1 summarizes the REINFORCE algorithm [2]. REINFORCE is a Monte Carlo algorithm. It does not require knowledge of the dynamics of the environment (in other words, model-free). Only experience samples, ,are needed to optimally tune the parameters of the policy network, . The discount factor, , takes into consideration the fact that rewards decrease in value as the number of steps increases. The gradient is discounted by . Gradients taken at later steps have smaller contributions. The learning rate, , is a scaling factor of the gradient update.

The parameters are updated by performing gradient ascent using the discounted gradient and learning rate. As a Monte Carlo algorithm...