This book strives to explain selected methods in deep learning, reinforcement learning, and deep reinforcement learning from a principled perspective. Through a series of progressively designed original experiments, readers are guided to independently program and implement these methods. The aim is to provide readers with a solid foundation in mastering deep reinforcement learning and applying these methods to solve real-world problems. The book is suitable not only for advanced undergraduate and graduate students majoring in Computer Science and Technology, Artificial Intelligence, Internet of Things Engineering, Data Science and Big Data, Software Engineering, Communications Engineering, Electronic Information, Robotics Engineering, Automation, Intelligent Manufacturing, and related fields for teaching and self-study, but also for practitioners and researchers in machine learning and enthusiasts for self-study and reference purposes.