This course covers theoretical foundations and state-of-the-art algorithms, and pratical applications in DRL, including machine learning basics, value-based methods, policy gradients, actor-critic methods, exploration, model-based RL, multi-agent RL, offline RL, inverse RL, and students will explore other recent research developments in RL contexts. The course emphasizes both theoretical rigor and practical implementation, featuring paper readings, critical discussions of recent research works, programming assignments using modern DRL frameworks, and a substantial research project. Upon completion, students will be equipped to understand current research literature, implement and analyze advanced DRL algorithms, and conduct independent research in the field.