The content of Reinforcement Learning is systematic and comprehensive, covering a wide range of topics, including theoretical elaboration, formula derivation, as well as abundant typical cases, so that theories are connected with practices. The book comprehensively and systematically describes the origin, background and classification of reinforcement learning, the principles and implementation of various reinforcement learning algorithms, as well as the relationship between implementation methods and algorithms, establishing a complete knowledge system of reinforcement learning for the readers; at the same time, it contains various classic cases, such as all kinds of maze treasure hunt, flappy birds, playing cards, mountain car, inverted pendulum, pendulum, GoBang, AlphaGo, AlphaGo Zero, AlphaZero and the like. By providing detailed descriptions of corresponding cases and code descriptions, it gives the readers an in-depth understanding of the essence of reinforcement learning algorithms.