Note: This is the website for a previous version of the class. You can find the current site here.
Deep RL, calculus of variations, and indirect methods for optimal control.
HJ Reachability, MPC, and an introduction to RL.
Q-learning, iterative LQR, and sequential convex programming.
Model-reference adaptive control, dynamic programming, and LQR.
This homework is not to be submitted; it is meant as a self-evaluation to test your knowledge.