CSE 5820: Reinforcement Learning

Reinforcement learning (RL) is a powerful paradigm for autonomous systems to learn to make decisions, and it is relevant to an enormous range of tasks, including robotics, game playing, consumer modeling and healthcare. This class will provide a solid introduction to the field of reinforcement learning and students will learn about the core concepts, design principles, widely used algorithms, RL with functional approximation, and generalization of RL. Through a combination of lectures, literature review, and written and coding assignments, students will become well versed in key ideas and techniques for RL including basics of reinforcement learning as well as deep reinforcement learning — an area that combines deep learning techniques with reinforcement learning.

Credits

3

Offered

Spring 2027

Campuses

Storrs

Requirements

CSE 4820 or CSE 5819; open to graduate students in the CSE program, others with consent. Recommended preparation: CSE 3500, MATH 2110Q, MATH 2210Q, and MATH 3160 or the equivalent.

Spring 2027 sections

Taught by Jonathan Ji.

Seats as of Nov 12, 2026. HuskyScheduler shows live seats when you search.

More courses

All CSE courses (Computer Science and Engineering) · All UConn subjects