Agenda

Learning for Dynamics and Control (L4DC)

Timings are in PDT

Day 1: Thursday, June 11th, 2020

08:30-08:35: Welcome and Introduction by organizers

08:35-09:05: Karen Willcox - Predictive digital twins: Where data-driven learning meets physics-based modeling

09:05-09:15: Break

09:15-10:15: Dynamics Learning II (4 talks)

10:15-10:30: Break

10:30-11:15: Policy Learning II (3 talks)

11:15-11:30: Break

11:30 – 12:00: Catherine Wolfram - Measuring the Socioeconomic Returns to High Quality Electricity

Day 2: Friday, June 12th, 2020

08:40-08:45: Welcome to 2nd Day by organizers

08:45-09:15: Leslie Kaelbling - Doing for our robots what nature did for us

09:15-09:45: John Lygeros - Data Enabled Predictive Control: Stochastic systems and implicit dynamic predictors

09:45-10:00: Break

10:00-11:00: Policy Learning I (4 talks)

10:45-11:00: Break

11:15-12:00: Dynamics Learning I (3 talks)

12:00 – 12:15: Break

12:15-12:45: Chelsea Finn - Extrapolation via Adaptation

Dynamics Learning Talks

Dynamics Learning I

Finite Sample System Identification: Optimal Rates and the Role of Regularization

Yue Sun, Samet Oymak and Maryam Fazel


Sample Complexity of Kalman Filtering for Unknown Systems

Anastasios Tsiamis, Nikolai Matni and George Pappas


A Spatially and Temporally Attentive Joint Trajectory Prediction Framework for Modeling Vessel Intent

Jasmine Sekhon and Cody Fleming


Dynamics Learning II

Learning to Correspond Dynamical Systems

Nam Hee Kim, Zhaoming Xie and Michiel van de Panne


Learning Dynamical Systems with Side Information

Amir Ali Ahmadi and Bachir El Khadir


Learning nonlinear dynamical systems from a single trajectory

Dylan Foster, Tuhin Sarkar and Alexander Rakhlin


Universal Simulation of Dynamical Systems by Recurrent Neural Nets

Joshua Hanson and Maxim Raginsky

Policy Learning Talks

Policy Learning I

Policy Optimization for H_2 Linear Control with H_infinity Robustness Guarantee: Implicit Regularization and Global Convergence

Kaiqing Zhang, Bin Hu and Tamer Basar


Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked Systems

Guannan Qu, Adam Wierman and Na Li


Learning Convex Optimization Control Policies

Akshay Agrawal, Shane Barratt, Stephen Boyd and Bartolomeo Stellato


Online Data Poisoning Attacks

Xuezhou Zhang, Xiaojin Zhu and Laurent Lessard


Policy Learning II

Data-driven distributionally robust LQR with multiplicative noise

Peter Coppens, Mathijs Schuurmans and Panagiotis Patrinos


Learning the model-free linear quadratic regulator via random search

Hesameddin Mohammadi, Mihailo R. Jovanovic' and Mahdi Soltanolkotabi


Optimistic robust linear quadratic dual control

Jack Umenberger and Thomas B Schon