Reinforcement Learning. 3 credits, 3 contact hours

Catalog description

Prerequisites: CS 375 or CS 370 . This course introduces students to reinforcement learning (RL), where agents learn to make decisions through interaction and feedback. Students explore the fundamentals of policies, value functions, Markov decision processes, and core learning methods such as dynamic programming, Monte Carlo, and temporal-difference updates. As an undergraduate level course, this course emphasizes intuitive understanding and guided practice rather than advanced mathematics or large-scale implementations. Through weekly conceptual exercises, students learn how RL agents learn from experience, evaluate simple algorithms, and apply basic RL ideas to real-world decision-making scenarios.