Book Image

Deep Learning with TensorFlow - Second Edition

By : Giancarlo Zaccone, Md. Rezaul Karim
Book Image

Deep Learning with TensorFlow - Second Edition

By: Giancarlo Zaccone, Md. Rezaul Karim

Overview of this book

Deep learning is a branch of machine learning algorithms based on learning multiple levels of abstraction. Neural networks, which are at the core of deep learning, are being used in predictive analytics, computer vision, natural language processing, time series forecasting, and to perform a myriad of other complex tasks. This book is conceived for developers, data analysts, machine learning practitioners and deep learning enthusiasts who want to build powerful, robust, and accurate predictive models with the power of TensorFlow, combined with other open source Python libraries. Throughout the book, you’ll learn how to develop deep learning applications for machine learning systems using Feedforward Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Autoencoders, and Factorization Machines. Discover how to attain deep learning programming on GPU in a distributed way. You'll come away with an in-depth knowledge of machine learning techniques and the skills to apply them to real-world projects.
Table of Contents (15 chapters)
Deep Learning with TensorFlow - Second Edition
Contributors
Preface
Other Books You May Enjoy
Index

Deep Q-learning


Thanks to the recent achievements of Google DeepMind in 2013 and 2016, which succeeded at reaching so-called superhuman levels in Atari games and beat the world champion Go, RL has become very interesting in of the machine learning community. This renewed interest is also due to the advent of Deep Neural Networks (DNNs) as approximation functions, bringing the potential value of this type of algorithm to an even higher level. The algorithm that has gained the most interest in recent times is definitely Deep Q-Learning. The following section introduces the Deep Q-Learning algorithm and also discusses some optimization techniques to maximize its performance.

Deep Q neural networks

The Q-learning base algorithm can cause tremendous problems when the number of states and possible actions increases and becomes unmanageable from a matrix point of view. Just think of the input configuration in the case of the structure used by Google to achieve the level of performance in the Atari...