EE5885 Deep Reinforcement Learning and Control

Fall 2020-2022, Spring 2024-2025

Course description: In recent years we have been witnessing the remarkable advances of deep networks, computing power and ready access to data, which make Deep Reinforcement Learning one of the most powerful tools for dealing with intelligent decision-making and control of autonomous systems. From the design of automatic control functionalities for robotics and self-driving vehicles to the development of sophisticated game AI, reinforcement has been used to develop a variety of cutting-edge technologies of both practical and theoretical interest. This course will provide a solid introduction to the field of deep reinforcement learning including the core principles, approaches and algorithms, and their applications in robotics, game playing, intelligent transportation, etc. Through a combination of lectures, exercises and a final course project, students will learn the key ideas and techniques for deep RL and gain hands-on experience coding and testing reinforcement systems on a variety of robot control problems.