Reinforcement Learning

Three credits · Graduate

This course will introduce the fundamentals of Reinforcement learning and Deep learning techniques. The course will cover the Tabular solution methods, such as the finite Markov Decision Processes and Temporal-Difference learning. It will also cover approximation solution methods, as on-policy and off-policy approximations. By the end of the course, new deep-learning techniques will be introduced. Strong fundamentals in calculus and data structure are recommended. Restricted to MACS and MSc- CSCI students. Three credits.