L4DC 2021

104 papers

Learning Finite-Dimensional Representations For Koopman Operators

Mohammad Khosravi

Regret-optimal measurement-feedback control

Gautam Goel, Babak Hassibi

Approximate Distributionally Robust Nonlinear Optimization with Application to Model Predictive Control: A Functional Approach

Yassine Nemmour, Bernhard Schölkopf, Jia-Jie Zhu

Robust Reinforcement Learning: A Constrained Game-theoretic Approach

Jing Yu, Clement Gehring, Florian Schäfer, Animashree Anandkumar

Learning Visually Guided Latent Actions for Assistive Teleoperation

Siddharth Karamcheti, Albert J. Zhai, Dylan P. Losey, Dorsa Sadigh

Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Data

Yaofeng Desmond Zhong, Biswadip dey, Amit Chakraborty

Optimal Cost Design for Model Predictive Control

Avik Jain, Lawrence Chan, Daniel S. Brown, Anca D. Dragan

Generating Adversarial Disturbances for Controller Verification

Udaya Ghai, David Snyder, Anirudha Majumdar, Elad Hazan

A New Objective for Identification of Partially Observed Linear Time-Invariant Dynamical Systems from Input-Output Data

Nicholas Galioto, Alex Arkady Gorodetsky

Adaptive Sampling for Estimating Distributions: A Bayesian Upper Confidence Bound Approach

Dhruva Kartik, Neeraj Sood, Urbashi Mitra, Tara Javidi

Offline Reinforcement Learning from Images with Latent Space Models

Rafael Rafailov, Tianhe Yu, Aravind Rajeswaran, Chelsea Finn

Forced Variational Integrator Networks for Prediction and Control of Mechanical Systems

Aaron Havens, Girish Chowdhary

Domain Adaptation Using System Invariant Dynamics Models

Sean J. Wang, Aaron M. Johnson

Fast Stochastic Kalman Gradient Descent for Reinforcement Learning

Simone Totaro, Anders Jonsson

SEAGuL: Sample Efficient Adversarially Guided Learning of Value Functions

Benoit Landry, Hongkai Dai, Marco Pavone

Safe Reinforcement Learning Using Robust Action Governor

Yutong Li, Nan Li, H. Eric Tseng, Anouck Girard, Dimitar Filev

Approximate Midpoint Policy Iteration for Linear Quadratic Control

Benjamin Gravell, Iman Shames, Tyler Summers

Learning How to Solve “Bubble Ball”

Hotae Lee, Monimoy Bujarbaruah, Francesco Borrelli

Faster Policy Learning with Continuous-Time Gradients

Samuel Ainsworth, Kendall Lowrey, John Thickstun, Zaïd Harchaoui, Siddhartha Srinivasa

Episodic Learning for Safe Bipedal Locomotion with Control Barrier Functions and Projection-to-State Safety

Noel Csomay-Shanklin, Ryan K. Cosner, Min Dai, Andrew J. Taylor, Aaron D. Ames

Contraction L1-Adaptive Control using Gaussian Processes

Aditya Gahlawat, Arun Lakshmanan, Lin Song, Andrew Patterson, Zhuohuan Wu

KPC: Learning-Based Model Predictive Control with Deterministic Guarantees

Emilio T. Maddalena, Paul Scharnhorst, Yuning Jiang, Colin N. Jones

Maximum Likelihood Signal Matrix Model for Data-Driven Predictive Control

Mingzhou Yin, Andrea Iannelli, Roy S. Smith

Offset-free setpoint tracking using neural network controllers

Patricia Pauli, Johannes Köhler, Julian Berberich, Anne Koch, Frank Allgöwer

Automating Discovery of Physics-Informed Neural State Space Models via Learning and Evolution

Elliott Skomski, Jan Drgona, Aaron Tuor

Finite-time System Identification and Adaptive Control in Autoregressive Exogenous Systems

Sahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar

How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?

Jingxi Xu, Bruce Lee, Nikolai Matni, Dinesh Jayaraman

Decoupling dynamics and sampling: RNNs for unevenly sampled data and flexible online predictions

Signe Moe, Camilla Sterud

Learning the Dynamics of Time Delay Systems with Trainable Delays

Xunbi A. Ji, Tamás G. Molnár, Sergei S. Avedisov, Gábor Orosz

Traffic Forecasting using Vehicle-to-Vehicle Communication

Steven Wong, Lejun Jiang, Robin Walters, Tamás G. Molnár, Gábor Orosz

On exploration requirements for learning safety constraints

Pierre-François Massiani, Steve Heim, Sebastian Trimpe

Minimax Adaptive Control for a Finite Set of Linear Systems

Anders Rantzer

Learning based attacks in Cyber Physical Systems: Exploration, Detection, and Control Cost trade-offs

Anshuka Rangi, Mohammad Javad Khojasteh, Massimo Franceschetti

Accelerated Concurrent Learning Algorithms via Data-Driven Hybrid Dynamics and Nonsmooth ODEs

Daniel E. Ochoa, Jorge I. Poveda, Anantharam Subbaraman, Gerd S. Schmidt, Farshad R. Pour-Safaei

Near-Optimal Data Source Selection for Bayesian Learning

Lintao Ye, Aritra Mitra, Shreyas Sundaram

Certifying Incremental Quadratic Constraints for Neural Networks via Convex Optimization

Navid Hashemi, Justin Ruths, Mahyar Fazlyab

Feedback from Pixels: Output Regulation via Learning-based Scene View Synthesis

Murad Abu-Khalaf, Sertac Karaman, Daniela Rus

Reward Biased Maximum Likelihood Estimation for Reinforcement Learning

Akshay Mete, Rahul Singh, Xi Liu, P. R. Kumar

Data-Driven Abstraction of Monotone Systems

Anas Makdesi, Antoine Girard, Laurent Fribourg

Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement Learning

Chenyu Liu, Yan Zhang, Yi Shen, Michael M. Zavlanos

Nested Mixture of Experts: Cooperative and Competitive Learning of Hybrid Dynamical System

Junhyeok Ahn, Luis Sentis

Linear Regression over Networks with Communication Guarantees

Konstantinos Gatsis

ARDL - A Library for Adaptive Robotic Dynamics Learning

Joshua Smith, Michael Mistry

Stable Online Control of Linear Time-Varying Systems

Guannan Qu, Yuanyuan Shi, Sahin Lale, Anima Anandkumar, Adam Wierman

Uncertain-aware Safe Exploratory Planning using Gaussian Process and Neural Control Contraction Metric

Dawei Sun, Mohammad Javad Khojasteh, Shubhanshu Shekhar, Chuchu Fan

Exploiting Sparsity for Neural Network Verification

Matthew Newton, Antonis Papachristodoulou

Primal-dual Learning for the Model-free Risk-constrained Linear Quadratic Regulator

Feiran Zhao, Keyou You

LEOC: A Principled Method in Integrating Reinforcement Learning and Classical Control Theory

Naifu Zhang, Nicholas Capel

Training deep residual networks for uniform approximation guarantees

Matteo Marchi, Bahman Gharesifard, Paulo Tabuada

Learning Stabilizing Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory

Lenart Treven, Sebastian Curi, Mojmir Mutny, Andreas Krause

Stability and Identification of Random Asynchronous Linear Time-Invariant Systems

Sahin Lale, Oguzhan Teke, Babak Hassibi, Anima Anandkumar

Accelerated Learning with Robustness to Adversarial Regressors

Joseph E. Gaudio, Anuradha M. Annaswamy, José M. Moreu, Michael A. Bolender, Travis E. Gibson

The Impact of Data on the Stability of Learning-Based Control

Armin Lederer, Alexandre Capone, Thomas Beckers, Jonas Umlauft, Sandra Hirche

Physics-penalised Regularisation for Learning Dynamics Models with Contact

Gabriella Pizzuto, Michael Mistry

Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Control

Yujie Tang, Yang Zheng, Na Li

Provably Sample Efficient Reinforcement Learning in Competitive Linear Quadratic Systems

Jingwei Zhang, Zhuoran Yang, Zhengyuan Zhou, Zhaoran Wang

Control of Unknown (Linear) Systems with Receding Horizon Learning

Christian Ebenbauer, Fabian Pfitz, Shuyou Yu

Chance-constrained quasi-convex optimization with application to data-driven switched systems control

Guillaume O. Berger, Raphaël M. Jungers, Zheming Wang

Sample Complexity of Linear Quadratic Gaussian (LQG) Control for Output Feedback Systems

Yang Zheng, Luca Furieri, Maryam Kamgarpour, Na Li

Suboptimal coverings for continuous spaces of control tasks

James A. Preiss, Gaurav S. Sukhatme

Learning-based feedforward augmentation for steady state rejection of residual dynamics on a nanometer-accurate planar actuator system

Ioannis Proimadis, Yorick Broens, Roland Tóth, Hans Butler

Nonlinear Data-Enabled Prediction and Control

Yingzhao Lian, Colin N. Jones

Adaptive Risk Sensitive Model Predictive Control with Stochastic Search

Ziyi Wang, Oswin So, Keuntaek Lee, Evangelos A. Theodorou

Safely Learning Dynamical Systems from Short Trajectories

Amir Ali Ahmadi, Abraar Chaudhry, Vikas Sindhwani, Stephen Tu

Self-Supervised Learning of Long-Horizon Manipulation Tasks with Finite-State Task Machines

Junchi Liang, Abdeslam Boularias

Regret Bounds for Adaptive Nonlinear Control

Nicholas M. Boffi, Stephen Tu, Jean-Jacques E. Slotine

Neural Lyapunov Redesign

Arash Mehrjou, Mohammad Ghavamzadeh, Bernhard Schölkopf

Accelerating Distributed SGD for Linear Regression using Iterative Pre-Conditioning

Kushal Chakrabarti, Nirupam Gupta, Nikhil Chopra

A Data Driven, Convex Optimization Approach to Learning Koopman Operators

Mario Sznaier

Learning Recurrent Neural Net Models of Nonlinear Systems

Joshua Hanson, Maxim Raginsky, Eduardo Sontag

When to stop value iteration: stability and near-optimality versus computation

Mathieu Granzotto, Romain Postoyan, Dragan Nešić, Lucian Busoniu, Jamal Daafouz

Certainty Equivalent Perception-Based Control

Sarah Dean, Benjamin Recht

Bridging Physics-based and Data-driven modeling for Learning Dynamical Systems

Rui Wang, Danielle Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu

The Dynamics of Gradient Descent for Overparametrized Neural Networks

Siddhartha Satpathi, R Srikant

Robust error bounds for quantised and pruned neural networks

Jiaqi Li, Ross Drummond, Stephen R. Duncan

Sequential Topological Representations for Predictive Models of Deformable Objects

Rika Antonova, Anastasia Varava, Peiyang Shi, J. Frederico Carvalho, Danica Kragic

Safe Reinforcement Learning of Control-Affine Systems with Vertex Networks

Liyuan Zheng, Yuanyuan Shi, Lillian J. Ratliff, Baosen Zhang

Probabilistic robust linear quadratic regulators with Gaussian processes

Alexander von Rohr, Matthias Neumann-Brosig, Sebastian Trimpe

Tight sampling and discarding bounds for scenario programs with an arbitrary number of removed samples

Licio Romao, Kostas Margellos, Antonis Papachristodoulou

Safe Bayesian Optimisation for Controller Design by Utilising the Parameter Space Approach

Lorenz Dörschel, David Stenger, Dirk Abel

Data-Driven Controller Design via Finite-Horizon Dissipativity

Nils Wieler, Julian Berberich, Anne Koch, Frank Allgöwer

A unified framework for Hamiltonian deep neural networks

Clara Lucía Galimberti, Liang Xu, Giancarlo Ferrari Trecate

Abstraction-based branch and bound approach to Q-learning for hybrid optimal control

Benoît Legat, Raphaël M. Jungers, Jean Bouchat

Input Convex Neural Networks for Building MPC

Felix Bünning, Adrian Schalbetter, Ahmed Aboudonia, Mathias Hudoba de Badyn, Philipp Heer

Nonlinear state-space identification using deep encoder networks

Gerben Beintema, Roland Tóth, Maarten Schoukens

Cautious Bayesian Optimization for Efficient and Scalable Policy Search

Lukas P. Fröhlich, Melanie N. Zeilinger, Edgar D. Klenske

On Uninformative Optimal Policies in Adaptive LQR with Unknown B-Matrix

Ingvar Ziemann, Henrik Sandberg

Learning Approximate Forward Reachable Sets Using Separating Kernels

Adam J. Thorpe, Kendric R. Ortiz, Meeko M. K. Oishi

Data-Driven System Level Synthesis

Anton Xue, Nikolai Matni

Learning local modules in dynamic networks

Paul M.J. Van den Hof, Karthik R. Ramaswamy

Data-Driven Reachability Analysis Using Matrix Zonotopes

Amr Alanwar, Anne Koch, Frank Allgöwer, Karl Henrik Johansson

Optimal Algorithms for Submodular Maximization with Distributed Constraints

Alexander Robey, Arman Adibi, Brent Schlotfeldt, Hamed Hassani, George J. Pappas

Non-conservative Design of Robust Tracking Controllers Based on Input-output Data

Liang Xu, Mustafa Sahin Turan, Baiwei Guo, Giancarlo Ferrari-Trecate

Learning to Actively Reduce Memory Requirements for Robot Control Tasks

Meghan Booker, Anirudha Majumdar

Graph Neural Networks for Distributed Linear-Quadratic Control

Fernando Gama, Somayeh Sojoudi

Data-driven design of switching reference governors for brake-by-wire applications

Andrea Sassella, Valentina Breschi, Simone Formentin

The benefits of sharing: a cloud-aided performance-driven framework to learn optimal feedback policies

Laura Ferrarotti, Valentina Breschi, Alberto Bemporad

Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-Reinforcement Learning

Kei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo

Learning Partially Observed Linear Dynamical Systems from Logarithmic Number of Samples

Salar Fattahi

Improved Analysis for Dynamic Regret of Strongly Convex and Smooth Functions

Peng Zhao, Lijun Zhang