Reinforcement Learning: Theory and Python Implementation is a tutorial book on reinforcement learning, with explanations of both theory and applications. Starting from a uniform mathematical framework, this book derives the theory of modern reinforcement learning in a systematic way and introduces all mainstream reinforcement learning algorithms including both classical reinforcement learning algorithms such as eligibility trace and deep reinforcement learning algorithms such as PPO, SAC, and MuZero. Every chapter is accompanied by high-quality implementations based on the latest version of Python packages such as Gym, and the implementations of deep reinforcement learning algorithms are all with both TensorFlow 2 and PyTorch 1. All codes can be found on GitHub along with their results and are runnable on a conventional laptop with either Windows, macOS, or Linux.

This book is intended for readers who want to learn reinforcement learning systematically and applyreinforcement learning to practical applications. It is also ideal to academical researchers who seek theoretical foundation or algorithm enhancement in their cutting-edge AI research.

Zhiqing Xiao obtained doctoral degree from Tsinghua University in 2016 and has more than 15 years in academic research and industrial practices on data-analytics and AI. He is the author of two AI bestsellers in Chinese: "Reinforcement Learning" and "Application of Neural Network and PyTorch" and published many academic papers. He also contributed to recent versions of the open-source software Gym.