This course focuses on theoretical and algorithmic foundations of reinforcement learning, through the lens of optimization, modern approximation, and learning theory. The course targets students with strong research interests in reinforcement learning, optimization under uncertainty, and data-driven control.
By the end of the course, students will be able to
There is no required textbook. Lectures and class discussions are mostly based on classical and recent papers on the topic.
RL textbooks:
Optimization foundations:
ML/AI foundations
Conferences and Workshop Proceedings