DSC624 Reinforcement Learning

[2–0, 2 cr.]

This course covers the fundamentals of reinforcement learning using a problem-based approach by addressing goal-directed problems on automated learning in an uncertain environment. Topics include finite Markov decision processes, dynamic programming, Monte-Carlo simulations, temporal-difference learning including Q-learning, function approximation, and policy gradient methods.

Pre-requisite: DSC602 Python for Data Science