CS 546 Reinforcement Learning

Students will learn fundamental concepts and techniques of Reinforcement Learning (RL), focusing on how agents learn optimal behaviors through environment interactions. Topics include Markov Decision Processes, Dynamic Programming, Monte Carlo Methods, Temporal-Difference Learning, and large-scale RL. Students will explore classic and contemporary RL algorithms, their applications, and state-of-the-art research. Hands-on experience will be gained by implementing RL algorithms, providing a full understanding of RL concepts and practical applications in various domains.