What this book covers

Chapter 1, Up and Running with Reinforcement Learning, introduces AI, RL, deep learning, the history/applications of the field, and other relevant topics. It will also provide a high-level overview of fundamental deep learning and TensorFlow concepts, especially those relevant to RL.

Chapter 2, Balancing Cart Pole, will have you implement your first RL algorithms in Python and TensorFlow to solve the cart pole balancing problem.

Chapter 3, Playing Atari Games, will get you creating your first deep RL algorithm to play ATARI games.

Chapter 4, Simulating Control Tasks, provides a brief introduction to actor-critic algorithms for continuous control problems. You will learn how to simulate classic control tasks, look at how to implement basic actor-critic algorithms, and understand the state-of-the-art algorithms for control.

Chapter 5, Building Virtual Worlds in Minecraft, takes the advanced concepts covered in previous chapters and applies them to Minecraft, a game more complex than those found on ATARI.

Chapter 6, Learning to Play Go, has you building a model that can play Go, the popular Asian board game that is considered one of the world's most complicated games.

Chapter 7, Creating a Chatbot, will teach you how to apply deep RL in natural language processing. Our reward function will be a future-looking function, and you will learn how to think in terms of probability when creating this function.

Chapter 8, Generating a Deep Learning Image Classifier, introduces one of the latest and most exciting advancements in RL: generating deep learning models using RL. We explore the cutting-edge research produced by Google Brain and implement the algorithms introduced.

Chapter 9, Predicting Future Stock Prices, discusses building an agent that can predict stock prices.

Chapter 10, Looking Ahead, concludes the book by discussing some of the real-world applications of reinforcement learning and introducing potential areas of future academic work.