We will discuss an emerging paradigm in differentiable reinforcement learning called “online nonstochastic control”. The new approach applies techniques from online convex optimization and convex relaxations to obtain new methods with provable guarantees for classical settings in optimal and robust control. Time permitting we will discuss recent extensions and insights into nonlinear control, iterative planning, and model free reinforcement learning. No background is needed for this talk, and an introductory textbook draft appears here. 

This theory was, and continues to be, developed here in Princeton with numerous collaborators, including Naman Agarwal, Brian Bullins, Karan Singh, Max Simchowitz, Xinyi Chen, Ani Majumdar, Sham Kakade, Edgar Minasyan, Paula Gradu, Jennifer Sun, and many others.