Course Description An introduction to the field of reinforcement learning (RL). Students will gain a comprehensive understanding of fundamental RL concepts, including Markov decision processes, dynamic programming, Monte Carlo methods, temporal-difference learning, and function approximation. The course will cover both model-based and model-free RL algorithms, exploring their theoretical foundations, practical implementations, and applications to real-world problems. Through readings and assignments, students will develop the ability to analyze, design, and implement RL agents for various tasks, building a deep understanding of this machine learning paradigm.
Reference Textbook Sutton & Barto. 2018. Reinforcement Learning: An Introduction. MIT Press. https://mitpress.mit.edu/9780262039246/reinforcement-learning/