This course explores the application of deep learning to sequential decision-making, including imitation learning, deep reinforcement learning (DRL), and agentic methods. The focus will be on the algorithmic advances over the last decade that have enabled superhuman performance in games (Atari, Go, StarCraft), have been effectively used to tune large language models (LLMs), and have been successfully applied to complex robotic and industrial control tasks. DRL (online and offline, model-free and model-based) and imitation learning (including diffusion policies and conditional flow matching) will be covered in depth, with more advanced topics (RLHF, RLVR, agentic control systems, and VLA models) also being discussed. Students will gain both theoretical knowledge of current strategies for learning-based control and hands-on experience implementing them.