Book Image

Reinforcement Learning with TensorFlow

By : Sayon Dutta
Book Image

Reinforcement Learning with TensorFlow

By: Sayon Dutta

Overview of this book

Reinforcement learning (RL) allows you to develop smart, quick and self-learning systems in your business surroundings. It's an effective method for training learning agents and solving a variety of problems in Artificial Intelligence - from games, self-driving cars and robots, to enterprise applications such as data center energy saving (cooling data centers) and smart warehousing solutions. The book covers major advancements and successes achieved in deep reinforcement learning by synergizing deep neural network architectures with reinforcement learning. You'll also be introduced to the concept of reinforcement learning, its advantages and the reasons why it's gaining so much popularity. You'll explore MDPs, Monte Carlo tree searches, dynamic programming such as policy and value iteration, and temporal difference learning such as Q-learning and SARSA. You will use TensorFlow and OpenAI Gym to build simple neural network models that learn from their own actions. You will also see how reinforcement learning algorithms play a role in games, image processing and NLP. By the end of this book, you will have gained a firm understanding of what reinforcement learning is and understand how to put your knowledge to practical use by leveraging the power of TensorFlow and OpenAI Gym.
Table of Contents (21 chapters)
Title Page
Packt Upsell


In this chapter, we covered the building blocks, such as shallow and deep neural networks that included logistic regression, single hidden layer neural network, RNNs, LSTMs, CNNs, and their other variations. Catering to the these topics, we also covered multiple activation functions, how forward and backward propagation works, and the problems associated with the training of deep neural networks, such as vanishing and exploding gradients.

Then, we covered the very basic terminologies in reinforcement learning that we will explore in detail in the coming chapters. These were the optimality criteria, which are value function and policy. We also gained an understanding of some reinforcement learning algorithms, such as Q-learning and A3C algorithms. Then, we covered some basic computations in the TensorFlow framework, an introduction to OpenAI Gym, and also discussed some of the influential pioneers and research breakthroughs in the field of reinforcement learning. 

In the following chapter, we will implement a basic reinforcement learning algorithm to a couple of OpenAI Gym framework environments and get a better understanding of OpenAI Gym.