MIE1630H: Reinforcement Learning for Research

This course is to provide fundamental concepts and mathematical frameworks for reinforcement learning. Specific topics include Markov decision processes, tabular reinforcement learning, policy gradient methods, function approximation, and model-based methods. The course is technical and intended for advanced students with a strong mathematical background and programming skills. Emphasis will be placed on recent developments and principled approaches.

0.50
MIE567H1 or MIE1615H or equivalent
St. George
In Class