Reinforcement Learning with Tensorflow

Reinforcement Learning with Tensorflow: Learn the art of designing self-learning systems with TensorFlow and OpenAI Gym

A Detailed Step-by-Step Guide covering Reinforcement Learning concepts, techniques and various frameworks to develop self learning systems

Key Features

• Become familiar with reinforcement learning concepts and learn how to implement them using TensorFlow
• Implement different problem-solving methods for Reinforcement Learning such as dynamic programming, Monte Carlo methods, and more
• Explore various reinforcement earning use-cases such as autonomous driving cars, robobrokers, and learning robots

Book Description

Reinforcement Learning (RL) is the next emerging area in the space of Artificial Intelligence and allows you to develop smart, quick and self-learning systems in your business surroundings. It is an effective method to train your learning agents and solve a variety of problems in Artificial Intelligence-from games, self-driving cars and robots to enterprise applications that range from datacenter energy saving (cooling data centers) to smart warehousing solutions.

The book covers the major advancements and successes achieved in deep reinforcement learning by synergizing deep neural network architectures with reinforcement learning. The book also introduces readers to the concept of Reinforcement Learning, its advantages and why it’s gaining so much popularity. Furthermore, it show readers how to put the concepts to practical use with the help of TensorFlow and OpenAI Gym to train efficient deep reinforcement learning neural networks. The book also discusses reinforcement learning and the rewarding system: Markov Decision Processes (MDPs), Monte Carlo tree searches, dynamic programming such as policy and value iteration, temporal difference learnings such as Q-learning and SARSA-

We see how reinforcement learning algorithms play a role in image processing and NLP, and how they can be used with TensorFlow and OpenAI Gym to build simple neural network models.

By the end of this book, you will have a firm understanding of what reinforcement learning is and how to put your knowledge to practical use by leveraging the power of TensorFlow and OpenAI Gym.

What you will learn

• Explore the applications of reinforcement learning in advertisement, image processing, and NLP
• Master various aspects of RL such as Deep-Q-Network, A3C, Q Learning, and more
• How Reinforcement Learning can be applied to robotics, autonomous vehicles, and finance.
• Frameworks and technologies to implement the various RL mechanisms
• Implement state-of-the-art RL algorithms from the basics
• Build pipelines, systems, and applications using RL techniques
• Teach an RL network to play a game using TensorFlow and/or the OpenAI gym framework
• Develop new systems that can learn, understand the environment, and make decisions

Who This Book Is For

If you want to get started with reinforcement learning using TensorFlow in the most practical way, this book will be a useful resource. The book assumes prior knowledge of machine learning and neural network programming concepts, as well as some understanding of the TensorFlow framework. No previous experience with Reinforcement Learning is required

Table of Contents

Chapter 1. Deep Learning; Architectures and Frameworks
Chapter 2. Training Reinforcement Learning Agents Using OpenAI Gym
Chapter 3. Markov Decision Process
Chapter 4. Policy Gradients
Chapter 5. Q-Learning and Deep Q-Networks
Chapter 6. Asynchronous Methods
Chapter 7. Robo Everything; Real Strategy Gaming
Chapter 8. AlphaGo; Reinforcement Learning at Its Best
Chapter 9. Reinforcement Learning in Autonomous Driving
Chapter 10. Financial Portfolio Management
Chapter 11. Reinforcement Learning in Robotics
Chapter 12. Deep Reinforcement Learning in Ad Tech
Chapter 13. Reinforcement Learning in Image Processing
Chapter 14. Deep Reinforcement Learning in NLP
Chapter 15. Further topics in Reinforcement Learning