Over the past two decades, advances in computing and communications have resulted in the creation, transmission and storage of data from all sectors of society. Over the next decade, the biggest generator of data is expected to be Internet-of-Things devices which sense and control the physical world. This explosion of data that is emerging from the physical world requires a rapprochement of areas such as machine learning, control theory, and optimization. The availability and scale of data, both temporal and spatial, brings a wonderful opportunity for our community to both advance the theory of control systems in a more data-driven fashion, as well as have a broader industrial and societal impact.

There are various challenges on the interface between the control community and the machine learning community. The goal of our workshop is to focus on what new ideas, approaches or questions can arise when learning theory is applied to control problems.In particular, our workshop goals are:

We are delighted to have assembled a world-class team of leading researchers working on the interface between machine learning and control.

The workshop will take place on Sunday December 16, 2018 during the 57th IEEE Conference on Decision and Control at the Fontainebleau in Miami Beach, FL, USA.

For accomodation information please visit the conference page.

Registration for the workshop can be made through this link at the 57th IEEE Conference on Decision and Control website. Please note that only people who have registered for the conference can register for the workshop. The conference early registration rate is till October 1st. The workshop fees are as follows:

Category Fee
Member170 USD
Non-Member170 USD
Life Member85 USD
Student85 USD
Retiree85 USD
Michael I. Jordan
University of California, Berkeley
Dimitri P. Bertsekas
Massachusetts Institute of Technology
Francesco Borrelli
University of California, Berkeley
Giuseppe Carlo Calafiore
Politecnico di Torino
Maryam Fazel
University of Washington

Frank L. Lewis
University of Texas at Arlington
Benjamin Recht
University of California, Berkeley
Angela Schoellig
University of Toronto
Claire J. Tomlin
University of California, Berkeley

Rene Vidal
Johns Hopkins University
Time Topic
8:45 - 8:50 Opening remarks by organizers
8:50 - 10:00

Session 1: Reinforcement Learning for Control - Chair: Pramod P. Khargonekar

8:50 - 9:25 Reinforcement Learning and Optimal Control: An Overview - Dimitri P. Bertsekas (Massachusetts Institute of Technology)

(link for book and slides)

9:25 - 10:00 Reinforcement Learning Structures for Real-Time Optimal Control and Differential Games - Frank L. Lewis (University of Texas at Arlington)

(link for slides)

10:00 - 10:30 Coffee Break
10:30 - 11:05

Session 1 continues

The Merits of Models in Continuous Reinforcement Learning - Benjamin Recht (University of California, Berkeley)

(link for slides)

11:05 - 12:05

Keynote Session - Chair: Manfred Morari

Dynamical, Symplectic and Stochastic Perspectives on Gradient-Based Optimization - Michael I. Jordan (University of California, Berkeley)

(link for slides)

12:00 - 1:30 Lunch Break
1:30 - 3:15

Session 2: Optimization and Statistical Learning - Chair: Konstantinos Gatsis

1:30 - 2:05 Dynamical Systems and the Alternating Direction Method of Multipliers - Rene Vidal (Johns Hopkins University)

(link for slides)

2:05 - 2:40 Convergence of Policy Gradient Methods for the Linear Quadratic Regulator - Maryam Fazel (University of Washington)

2:40 - 3:15 Scenario Optimization for Robust Design - foundations and recent developments - Giuseppe Carlo Calafiore (Politecnico di Torino)

(link for slides)

3:15 - 3:30 Coffee Break
3:30 - 5:15

Session 3: Safe Learning for Control - Chair: George J. Pappas

3:30 - 4:05 Safe model-based learning for robot control - Angela Schoellig (University of Toronto)

(link for slides)

4:05 - 4:40 Learning Model Predictive Control - Francesco Borrelli (University of California, Berkeley)

(link for slides)

4:40 - 5:15 Safe Learning in Robotics - Claire J. Tomlin (University of California, Berkeley)

5:15 - 5:30 Closing remarks by organizers
Konstantinos Gatsis
Konstantinos Gatsis
University of Pennsylvania
Pramod P. Khargonekar
University of California, Irvine
Manfred Morari
University of Pennsylvania
George J. Pappas
University of Pennsylvania

Should you have any questions, please do not hesitate to contact the organizers.