This book will cover interesting topics in deep Reinforcement Learning (RL), including the more widely used algorithms, and will also provide TensorFlow code to solve many challenging problems using deep RL algorithms. Some basic knowledge of RL will help you pick up the advanced topics covered in this book, but the topics will be explained in a simple language that machine learning practitioners can grasp. The language of choice for this book is Python, and the deep learning framework used is TensorFlow, and we expect you to have a reasonable understanding of the two. If not, there are several Packt books that cover these topics. We will cover several different RL algorithms, such as Deep Q-Network (DQN), Deep Deterministic Policy Gradient (DDPG), Trust Region Policy Optimization (TRPO), and Proximal Policy Optimization (PPO), to name a few. Let's dive right into deep RL.
In this chapter, we will delve deep into the basic concepts of RL. We will learn the meaning of the RL jargon, the mathematical relationships between them, and also how to use them in an RL setting to train an agent. These concepts will lay the foundations for us to learn RL algorithms in later chapters, along with how to apply them to train agents. Happy learning!
Some of the main topics that will be covered in this chapter are as follows:
- Formulating the RL problem
- Understanding what an agent and an environment are
- Defining the Bellman equation
- On-policy versus off-policy learning
- Model-free versus model-based training