AI 448 Reinforcement Learning

This course introduces students to topics in reinforcement learning. The course will begin with fundamental concepts in reinforcement learning, including Markov Decision Process and dynamic programming. The course will continue to focus on sampling-based learning techniques, including Monte Carlo methods, Temporal-Difference Learning, Q-learning, model-based learning, and later Deep Reinforcement Learning. The contents will also include On-policy methods and policy gradient methods.

Cross Listed Courses

CSC 448, CSC 548, AI 448