ECE3811 Reinforcement learning for engineers

This unit introduces you to the foundational principles and practice of reinforcement learning and its application to sequential decision-making problems in complex dynamic systems. Topics include reinforcement learning fundamentals (Markov decision process, Bellman equation, value and policy iteration), Q-learning, actor-critic methods, policy gradient, and imitation learning. You will also examine practical approaches for implementing these methods, including deep learning-based reinforcement learning, exploration-exploitation strategies, and reward function design. Throughout the course, you will learn how these methods are applied to solve planning, control, and optimisation problems in simulated engineering environments, and develop the necessary skills to enable modern intelligent decision-making systems.