Posters

• Murad Abu-Khalaf, Sertac Karaman & Daniela Rus, MIT, “Shared Linear Quadratic Regulation Control: A Reinforcement Learning Approach” PDF
• Aaron Ames & Andrew J. Taylor, CalTech, “A Control Lyapunov Function Approach to Episodic Learning” PDF
• Anuradha M. Annaswamy, MIT, “Stable and Fast Learning with Momentum and Adaptive Rates” PDF
• Thomas Beckers, Technical University of Munich, “Gaussian Process Based Identification and Control with Formal Guarantees” PDF
• Kostas Bekris, Rutgers University, “Closing the Reality Gap of Physics-Based Robot Simulation Through Task-Oriented Bayesian Optimization”
• Julian Berberich, University of Stuttgart, “Data-Driven Model Predictive Control with Stability and Robustness Guarantees” PDF
• Tom Bertalan, MIT, “On Learning Hamiltonian Systems from Data”
• Calin Belta & Xiao Li, Boston University, “A Formal Methods Approach to Reinforcement Learning For Robotic Control”
• Sushmita Bhattacharya & Thomas Wheeler, Arizona State University, “Reinforcement Learning for POMDP: Rollout and Policy Iteration with Application to Sequential Repair” PDF
• Nicholas M. Boffi, Harvard University, and Jean-Jacques Slotine, MIT, “A continuous-time analysis of distributed stochastic gradient”
• Byron Boots, Georgia Institute of Technology, “An Online Learning Approach to Model Predictive Control”
• Octavia Camps, Northeastern University College of Engineering, “KW-DYAN: A Recurrent Dynamics-Based Network for Video Prediction” PDF
• Bugra Can, Rutgers University, “Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances”
• Pratik Chaudhari, Amazon Web Services, “P3O: Policy-on Policy-off Policy Optimization”
• Alessandro Chiuso, University of Padova, “CoRe: Control Oriented Learning – A Regularisation-Based Approach”
• Glen Chou, University of Michigan, “Learning Constraints from Demonstrations”
• Claus Danielson, Ankush Chakrabarty, Stefano Di Cairano, Mitsubishi Electric Research Laboratories, “Invariance for Safe Learning in Constraint-Enforcing Control” PDF
• Adithya Devraj, University of Florida, “Stochastic Approximation and the Need for Speed” PDF
• Vikas Dhiman, UC San Diego, “Model-based Transfer Learning of Skills across Robots and Tools”
• Zhe Du, University of Michigan, “Online Robust Switched System Identification”
• Alec Farid, Princeton University, “PAC-Bayes Control: Learning Policies that Provably Generalize to Novel Environments” PDF
• Dylan Foster, MIT, “Model Selection for Contextual Bandits”
• Travis Gibson, Harvard Medical School, “Connections Between Adaptive Control and Machine Learning”
• Mert Gurbuzbalaban, Rutgers University, “Robust Accelerated Gradient Methods”
• Josiah Hanna, University of Texas, “Robot Learning in Simulation with Action Transformations”
• Hamed Hassani, University of Pennsylvania, “Distributed Scenarios in Submodular Optimization”
• Jonathan How, MIT, “Knowledge Transfer via Learning to Teach in Cooperative Multiagent Reinforcement Learning”
• Ameya Jagtap, Brown University, “Time-Parallel and Fractional Physics-Informed Neural Networks for Solving Transient PDEs” PDF
• Yassir Jedra, KTH Royal Institute of Technology in Stockholm, “Sample Complexity Lower Bounds for Linear System Identification”
• Angjoo Kanazawa, UC Berkeley, “SFV: Reinforcement Learning of Physical Skills from Videos” PDF
• Bahir El Kadir & Amir Ali Ahmadi, Princeton University, “Learning Dynamical Systems With Side Information”
• Reza Khodayi-mehr, Duke University, “Model-Based Learning of Turbulent Flows using Mobile Robots” PDF
• Dong-Ki Kim, MIT, “Knowledge Transfer via Learning to Teach in Cooperative Multiagent Reinforcement Learning”
• George Kissas & Yibo Yang, University of Pennsylvania, “Learning the Flow Map of Dynamical Systems with Self-Supervised Neural Runge-Kutta Networks”
• Alec Koppel, University of Pennsylvania, “Global Convergence of Policy Gradient Methods: A Nonconvex Optimization Perspective”
• Abdul Rahman Kreidieh, UC Berkeley, “Scalable methods for the control of mixed autonomous system”
• Nevena Lazic, Google, “POLITEX: Regret Bounds for Policy Iteration using Expert Prediction” PDF
• Armin Lederer, Technical University of Munich, “Stable Feedback Linearization and Optimal Control for Gaussian Processes” PDF
• Na Li, Harvard University, “The Role of Prediction in Online Control”
• Jason Liang, MIT, “Learning the Contextual Demand Curve in Repeated Auctions”  
• Nikolai Matni, UC Berkeley, “Robust Guarantees for Perception-Based Control”
• Jared Miller, Yang Zheng, Biel Roig-Solvas, Mario Sznaier, Antonis Papachristodoulou, Northeastern University/Harvard University/University of Oxford, “Chordal Decomposition in Rank Minimized SDPs” PDF
• Yannis Paschalidis, Boston University, “Distributionally Robust Learning and Applications to Predictive and Prescriptive Health Analytics” PDF
• Panagiotis Patrinos & Mathijs Schuurmans, KU Leuven, “Safe Learning-Based Control of Stochastic Jump Linear Systems: A Distributionally Robust Approach” PDF
• Amirhossein Reisizadeh, UC Santa Barbara, “Robust and Communication-Efficient Collaborative Learning” PDF
• Anders Rantzer, Lund University, “On the Non-Robustness of Certainty Equivalence Control”
• Lilian Ratliff, Sam Burden, Sam Coogan, Benjamin Chasnov & Tanner Fiez, University of Washington, “Certifiable Algorithms for Learning and Control in Multiagent Systems” PDF
• Alejandro Ribeiro, University of Pennsylvania, “Know Your Limits: Learning Feasible Specifications Using Counterfactual Optimization”
• Thomas Schön, Uppsala University, “Robust Exploration for Data-Driven Linear Quadratic Control”
• Artin Spiridonof, Boston University, “Network Independence in Distributed Optimization” PDF
• Lili Su, MIT, “Distributed Learning and Estimation in the Presence of Byzantine Agents”
• Friedrich Solowjow & Sebastian Trimpe, Max Planck Institute for Intelligent Systems – Stuttgart, Germany, “Event-Triggered Learning”
• Karan Singh, Princeton University, “Online Control with Adversarial Disturbances”
• Madeleine Udell, Cornell University, “OBOE: Collaborative Filtering for Automated Machine Learning” PDF
• Min Wen, University of Pennsylvania, “Constrained Cross-Entropy Method for Safe Reinforcement Learning”
• Zhi Xu, MIT, “On Reinforcement Learning Using Monte Carlo Tree Search with Supervised Learning: Non-Asymptotic Analysis”
• Lin F. Yang, Princeton University, “Sample-Optimal Parametric Q-Learning with Linear Transition Models” PDF
• Yan Zhang, Duke University, “Distributed Off-Policy Actor-Critic Reinforcement Learning with Policy Consensus”