ENGS 101 - Principles of Reinforcement Learning

Reinforcement learning (RL) is a set of algorithms within AI that focuses on how agents can learn to make decisions by interacting with their environment. Unlike supervised learning, reinforcement learning does not rely on labeled input/output pairs. Instead, agents learn from feedback in the form of rewards or penalties. While the behavior of RL systems can sometimes seem unpredictable, this course will make clear that reinforcement learning is based on solid mathematical and engineering foundations, with a wide range of practical applications. This course will focus on the mathematics, core theories, and algorithmic principles behind reinforcement learning. The goal of this course is to build a strong theoretical foundation for understanding how reinforcement learning works, both in theory and in practice. The methods we study will have relevance for real-world problems in robotics, game playing, control systems, healthcare, and behavioral modeling, among others.

Multivariable calculus (MATH 8 or MATH 9); Linear algebra (MATH 22 or MATH 24); Probability (MATH 20, ENGS 93, or ENGG 193); and ENGS 20 or COSC 10. ENGS 96 is encouraged.