MATH 5796 REINFORCEMENT LEARNING
Reinforcement learning is an area of machine learning where an agent learns by taking actions in an environment. Reinforcement learning is most famously known as the backbone behind classic Go engines such as Google DeepMind’s AlphaGo, and modern chess engines such as Stockfish, but it is also used in fields such as autonomous driving. This course will provide a solid introduction to the field of reinforcement learning and students will learn about the core challenges and approaches, including generalization and exploration. This course requires the use of computers for coding assignments.
Prerequisite
MATH*3544 or Instructor’s approval