ORIE 6590: Approximate Dynamic Programming and Reinforcement Learning

This course covers both theory and practice for optimal sequential decision making under uncertainty. We will begin with foundations of sequential decision making and Markov Decision Processes and then move on to recent approaches for large-scale reinforcement learning. The emphasis will be on both conceptual understanding of design principles and implementation/application of these algorithms. We will read recently published articles on RL and utilize those ideas to potentially improve our implementations.