Lectures

Lecture 1 (08/22/2023): An Overview of "Control for Learing"

Slide

Lecture 2 (08/24/2023): An Overview of "Learning for Control"

Slide

Lecture 3 (08/29/2023): Unifying the Analysis in Control and Optimization via Semidefinite Programs, Part I

Lecture Note

Lecture 4 (08/31/2023): Unifying the Analysis in Control and Optimization via Semidefinite Programs, Part II

Lecture Note, Main Reference I, Main Reference II

Lecture 5 (09/05/2023): Policy-Based Reinforcement Learning for Control, Part I

Lecture Note

Lecture 6 (09/07/2023): Policy-Based Reinforcement Learning for Control, Part II

Lecture Note, Main Reference

Lecture 7 (09/12/2023): A Control Perspective on Certifiably Robust Neural Networks, Part I

Lecture Note, Main Reference

Lecture 8 (09/14/2023): A Control Perspective on Certifiably Robust Neural Networks, Part II

Lecture Note

Lecture 9 (09/19/2023): Control Barrier Functions for Safety of Perception-Based Control, Part I

Lecture Note, Main Reference

Lecture 10 (09/21/2023): Control Barrier Functions for Safety of Perception-Based Control, Part II

Lecture Note

Lecture 11 (09/26/2023): Control Tools for Stochastic Optimization and Supervised Learning, Part I

Lecture Note, Main Reference

Lecture 12 (09/28/2023): Control Tools for Stochastic Optimization and Supervised Learning, Part II

Lecture Note, Main Reference

Lecture 13 (10/03/2023): Imitation Learning for Control, Part I

Lecture Note, Main Reference, Video for Main Reference

Lecture 14 (10/05/2023): Imitation Learning for Control, Part II

We will use the slides from Prof. Lars Lindemann (USC). The slides will be distributed via email.

Main Reference

Lecture 15 (10/10/2023): A Jump System Perspective on Temporal Difference Learning, Part I

Lecture Note, Main Reference

Lecture 16 (10/12/2023): A Jump System Perspective on Temporal Difference Learning, Part II

Lecture Note

Lecture 17 (10/17/2023): Online Learning for Control, Part I

ICML Tutorial from Prof. Elad Hazan and Karan Singh

Lecture 18 (10/19/2023): Online Learning for Control, Part II

Main Reference

Lecture 19 (10/24/2023): Robust Control Tools for Distributed Optimization, Part I

Main Reference: Pages 47-58 of Prof. Laurent Lessard's Slides, A Simplifed Version of the Results

Lecture 20 (10/26/2023): Robust Control Tools for Distributed Optimization, Part II

Main Reference

Lecture 21 (10/31/2023): Statistical Learning Theory for System ID and Control, Part I

Main Reference: Prof. Stephen Tu's Tutorial slides

Lecture 22 (11/02/2023): Statistical Learning Theory for System ID and Control, Part II

Main Reference 1, Main Reference 2

Lecture 23 (11/07/2023): Diffusion Models and An Optimal Control Interpretation, Part I

Main Reference: CVPR 2023 Tutorial on Diffusion Models

Lecture 24 (11/09/2023): Diffusion Models and An Optimal Control Interpretation, Part II

Main Reference: Chapter 7 of Prof. Maxim Raginsky's SDE Book

Lecture 25 (11/14/2023): Neural Certificates for Control Systems, Part I

Main Reference 1, Main Reference 2

Lecture 26 (11/16/2023): Neural Certificates for Control Systems, Part II

Main Reference

Lecture 27 (11/28/2023): Intersection of Large Language Models and Feedback Control, Part I

A List of Useful Materials

Lecture 28 (11/30/2023): Intersection of Large Language Models and Feedback Control, Part II

A List of Useful Materials

Lecture 29 (12/05/2023): Summary and Future Directions