Table of Contents

• PrefaceAli Jadbabaie, John Lygeros, George J. Pappas, Pablo A. Parrilo, Benjamin Recht, Claire J. Tomlin, Melanie N. Zeilinger. 1-5 [doi]
• On the model-based stochastic value gradient for continuous reinforcement learningBrandon Amos, Samuel Stanton, Denis Yarats, Andrew Gordon Wilson. 6-20 [doi]
• Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement LearningAnoopkumar Sonar, Vincent Pacelli, Anirudha Majumdar. 21-33 [doi]
• Learning-based State Reconstruction for a Scalar Hyperbolic PDE under noisy Lagrangian SensingMatthieu Barreau, John Liu, Karl Henrik Johansson. 34-46 [doi]
• Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time PerformanceThinh T. Doan. 47 [doi]
• Improved Analysis for Dynamic Regret of Strongly Convex and Smooth FunctionsPeng Zhao, Lijun Zhang. 48-59 [doi]
• Learning Partially Observed Linear Dynamical Systems from Logarithmic Number of SamplesSalar Fattahi. 60-72 [doi]
• Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-Reinforcement LearningKei Akuzawa, Yusuke Iwasawa, Yutaka Matsuo. 73-86 [doi]
• The benefits of sharing: a cloud-aided performance-driven framework to learn optimal feedback policiesLaura Ferrarotti, Valentina Breschi, Alberto Bemporad. 87-98 [doi]
• Data-driven design of switching reference governors for brake-by-wire applicationsAndrea Sassella, Valentina Breschi, Simone Formentin. 99-110 [doi]
• Graph Neural Networks for Distributed Linear-Quadratic ControlFernando Gama, Somayeh Sojoudi. 111-124 [doi]
• Learning to Actively Reduce Memory Requirements for Robot Control TasksMeghan Booker, Anirudha Majumdar. 125-137 [doi]
• Non-conservative Design of Robust Tracking Controllers Based on Input-output DataLiang Xu, Mustafa Sahin Turan, Baiwei Guo, Giancarlo Ferrari-Trecate. 138-149 [doi]
• Optimal Algorithms for Submodular Maximization with Distributed ConstraintsAlexander Robey, Arman Adibi, Brent Schlotfeldt, Hamed Hassani, George J. Pappas. 150-162 [doi]
• Data-Driven Reachability Analysis Using Matrix ZonotopesAmr Alanwar, Anne Koch, Frank Allgöwer, Karl Henrik Johansson. 163-175 [doi]
• Learning local modules in dynamic networksPaul M. J. Van den Hof, Karthik R. Ramaswamy. 176-188 [doi]
• Data-Driven System Level SynthesisAnton Xue, Nikolai Matni. 189-200 [doi]
• Learning Approximate Forward Reachable Sets Using Separating KernelsAdam J. Thorpe, Kendric R. Ortiz, Meeko M. K. Oishi. 201-212 [doi]
• On Uninformative Optimal Policies in Adaptive LQR with Unknown B-MatrixIngvar Ziemann, Henrik Sandberg. 213-226 [doi]
• Cautious Bayesian Optimization for Efficient and Scalable Policy SearchLukas P. Fröhlich, Melanie N. Zeilinger, Edgar D. Klenske. 227-240 [doi]
• Nonlinear state-space identification using deep encoder networksGerben Beintema, Roland Tóth, Maarten Schoukens. 241-250 [doi]
• Input Convex Neural Networks for Building MPCFelix Bünning, Adrian Schalbetter, Ahmed Aboudonia, Mathias Hudoba de Badyn, Philipp Heer, John Lygeros. 251-262 [doi]
• Abstraction-based branch and bound approach to Q-learning for hybrid optimal controlBenoît Legat, Raphaël M. Jungers, Jean Bouchat. 263-274 [doi]
• A unified framework for Hamiltonian deep neural networksClara Lucía Galimberti, Liang Xu, Giancarlo Ferrari-Trecate. 275-286 [doi]
• Data-Driven Controller Design via Finite-Horizon DissipativityNils Wieler, Julian Berberich, Anne Koch, Frank Allgöwer. 287-298 [doi]
• Safe Bayesian Optimisation for Controller Design by Utilising the Parameter Space ApproachLorenz Dörschel, David Stenger, Dirk Abel. 299-311 [doi]
• Tight sampling and discarding bounds for scenario programs with an arbitrary number of removed samplesLicio Romao, Kostas Margellos, Antonis Papachristodoulou. 312-323 [doi]
• Probabilistic robust linear quadratic regulators with Gaussian processesAlexander von Rohr, Matthias Neumann-Brosig, Sebastian Trimpe. 324-335 [doi]
• Safe Reinforcement Learning of Control-Affine Systems with Vertex NetworksLiyuan Zheng, Yuanyuan Shi, Lillian J. Ratliff, Baosen Zhang. 336-347 [doi]
• Sequential Topological Representations for Predictive Models of Deformable ObjectsRika Antonova, Anastasiia Varava, Peiyang Shi, J. Frederico Carvalho, Danica Kragic. 348-360 [doi]
• Robust error bounds for quantised and pruned neural networksJiaqi Li, Ross Drummond, Stephen R. Duncan. 361-372 [doi]
• The Dynamics of Gradient Descent for Overparametrized Neural NetworksSiddhartha Satpathi, Rayadurgam Srikant. 373-384 [doi]
• Bridging Physics-based and Data-driven modeling for Learning Dynamical SystemsRui Wang, Danielle C. Maddix, Christos Faloutsos, Yuyang Wang, Rose Yu. 385-398 [doi]
• Certainty Equivalent Perception-Based ControlSarah Dean, Benjamin Recht. 399-411 [doi]
• When to stop value iteration: stability and near-optimality versus computationMathieu Granzotto, Romain Postoyan, Dragan Nesic, Lucian Busoniu, Jamal Daafouz. 412-424 [doi]
• Learning Recurrent Neural Net Models of Nonlinear SystemsJoshua Hanson, Maxim Raginsky, Eduardo D. Sontag. 425-435 [doi]
• A Data Driven, Convex Optimization Approach to Learning Koopman OperatorsMario Sznaier. 436-446 [doi]
• Accelerating Distributed SGD for Linear Regression using Iterative Pre-ConditioningKushal Chakrabarti, Nirupam Gupta, Nikhil Chopra. 447-458 [doi]
• Neural Lyapunov RedesignArash Mehrjou, Mohammad Ghavamzadeh, Bernhard Schölkopf. 459-470 [doi]
• Regret Bounds for Adaptive Nonlinear ControlNicholas M. Boffi, Stephen Tu, Jean-Jacques E. Slotine. 471-483 [doi]
• Self-Supervised Learning of Long-Horizon Manipulation Tasks with Finite-State Task MachinesJunchi Liang, Abdeslam Boularias. 484-497 [doi]
• Safely Learning Dynamical Systems from Short TrajectoriesAmir Ali Ahmadi, Abraar Chaudhry, Vikas Sindhwani, Stephen Tu. 498-509 [doi]
• Adaptive Risk Sensitive Model Predictive Control with Stochastic SearchZiyi Wang, Oswin So, Keuntaek Lee, Evangelos A. Theodorou. 510-522 [doi]
• Nonlinear Data-Enabled Prediction and ControlYing Zhao Lian, Colin N. Jones. 523-534 [doi]
• Learning-based feedforward augmentation for steady state rejection of residual dynamics on a nanometer-accurate planar actuator systemIoannis Proimadis, Yorick Broens, Roland Tóth, Hans Butler. 535-546 [doi]
• Suboptimal coverings for continuous spaces of control tasksJames A. Preiss, Gaurav S. Sukhatme. 547-558 [doi]
• Sample Complexity of Linear Quadratic Gaussian (LQG) Control for Output Feedback SystemsYang Zheng, Luca Furieri, Maryam Kamgarpour, Na Li 0002. 559-570 [doi]
• Chance-constrained quasi-convex optimization with application to data-driven switched systems controlGuillaume O. Berger, Raphaël M. Jungers, Zheming Wang. 571-583 [doi]
• Control of Unknown (Linear) Systems with Receding Horizon LearningChristian Ebenbauer, Fabian Pfitz, Shuyou Yu 0001. 584-596 [doi]
• Provably Sample Efficient Reinforcement Learning in Competitive Linear Quadratic SystemsJingwei Zhang, Zhuoran Yang, Zhengyuan Zhou, Zhaoran Wang. 597-598 [doi]
• Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) ControlYujie Tang, Yang Zheng, Na Li. 599-610 [doi]
• Physics-penalised Regularisation for Learning Dynamics Models with ContactGabriella Pizzuto, Michael N. Mistry. 611-622 [doi]
• The Impact of Data on the Stability of Learning-Based ControlArmin Lederer, Alexandre Capone, Thomas Beckers, Jonas Umlauft, Sandra Hirche. 623-635 [doi]
• Accelerated Learning with Robustness to Adversarial RegressorsJoseph E. Gaudio, Anuradha M. Annaswamy, José M. Moreu, Michael A. Bolender, Travis E. Gibson. 636-650 [doi]
• Stability and Identification of Random Asynchronous Linear Time-Invariant SystemsSahin Lale, Oguzhan Teke, Babak Hassibi, Anima Anandkumar. 651-663 [doi]
• Learning Stabilizing Controllers for Unstable Linear Quadratic Regulators from a Single TrajectoryLenart Treven, Sebastian Curi, Mojmír Mutný, Andreas Krause 0001. 664-676 [doi]
• Training deep residual networks for uniform approximation guaranteesMatteo Marchi, Bahman Gharesifard, Paulo Tabuada. 677-688 [doi]
• LEOC: A Principled Method in Integrating Reinforcement Learning and Classical Control TheoryNaifu Zhang, Nicholas Capel. 689-701 [doi]
• Primal-dual Learning for the Model-free Risk-constrained Linear Quadratic RegulatorFeiran Zhao, Keyou You. 702-714 [doi]
• Exploiting Sparsity for Neural Network VerificationMatthew Newton, Antonis Papachristodoulou. 715-727 [doi]
• Uncertain-aware Safe Exploratory Planning using Gaussian Process and Neural Control Contraction MetricDawei Sun, Mohammad Javad Khojasteh, Shubhanshu Shekhar, Chuchu Fan. 728-741 [doi]
• Stable Online Control of Linear Time-Varying SystemsGuannan Qu, Yuanyuan Shi, Sahin Lale, Anima Anandkumar, Adam Wierman. 742-753 [doi]
• ARDL - A Library for Adaptive Robotic Dynamics LearningJoshua Smith, Michael N. Mistry. 754-766 [doi]
• Linear Regression over Networks with Communication GuaranteesKonstantinos Gatsis. 767-778 [doi]
• Nested Mixture of Experts: Cooperative and Competitive Learning of Hybrid Dynamical SystemJunhyeok Ahn, Luis Sentis. 779-790 [doi]
• Learning without Knowing: Unobserved Context in Continuous Transfer Reinforcement LearningChenyu Liu, Yan Zhang 0043, Yi Shen, Michael M. Zavlanos. 791-802 [doi]
• Data-Driven Abstraction of Monotone SystemsAnas Makdesi, Antoine Girard, Laurent Fribourg. 803-814 [doi]
• Reward Biased Maximum Likelihood Estimation for Reinforcement LearningAkshay Mete, Rahul Singh, Xi Liu, P. R. Kumar 0001. 815-827 [doi]
• Feedback from Pixels: Output Regulation via Learning-based Scene View SynthesisMurad Abu-Khalaf, Sertac Karaman, Daniela Rus. 828-841 [doi]
• Certifying Incremental Quadratic Constraints for Neural Networks via Convex OptimizationNavid Hashemi, Justin Ruths, Mahyar Fazlyab. 842-853 [doi]
• Near-Optimal Data Source Selection for Bayesian LearningLintao Ye, Aritra Mitra, Shreyas Sundaram. 854-865 [doi]
• Accelerated Concurrent Learning Algorithms via Data-Driven Hybrid Dynamics and Nonsmooth ODEsDaniel Esteban Ochoa, Jorge I. Poveda, Anantharam Subbaraman, Gerd S. Schmidt, Farshad R. Pour Safaei. 866-878 [doi]
• Learning based attacks in Cyber Physical Systems: Exploration, Detection, and Control Cost trade-offsAnshuka Rangi, Mohammad Javad Khojasteh, Massimo Franceschetti. 879-892 [doi]
• Minimax Adaptive Control for a Finite Set of Linear SystemsAnders Rantzer. 893-904 [doi]
• On exploration requirements for learning safety constraintsPierre-François Massiani, Steve Heim, Sebastian Trimpe. 905-916 [doi]
• Traffic Forecasting using Vehicle-to-Vehicle CommunicationSteven Wong, Lejun Jiang, Robin Walters, Tamás G. Molnár, Gábor Orosz, Rose Yu. 917-929 [doi]
• Learning the Dynamics of Time Delay Systems with Trainable DelaysXunbi A. Ji, Tamás G. Molnár, Sergei S. Avedisov, Gábor Orosz. 930-942 [doi]
• Decoupling dynamics and sampling: RNNs for unevenly sampled data and flexible online predictionsSigne Moe, Camilla Sterud. 943-953 [doi]
• How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?Jingxi Xu, Bruce Lee, Nikolai Matni, Dinesh Jayaraman. 954-966 [doi]
• Finite-time System Identification and Adaptive Control in Autoregressive Exogenous SystemsSahin Lale, Kamyar Azizzadenesheli, Babak Hassibi, Anima Anandkumar. 967-979 [doi]
• Automating Discovery of Physics-Informed Neural State Space Models via Learning and EvolutionElliott Skomski, Jan Drgona, Aaron Tuor. 980-991 [doi]
• Offset-free setpoint tracking using neural network controllersPatricia Pauli, Johannes Köhler, Julian Berberich, Anne Koch, Frank Allgöwer. 992-1003 [doi]
• Maximum Likelihood Signal Matrix Model for Data-Driven Predictive ControlMingzhou Yin, Andrea Iannelli, Roy S. Smith. 1004-1014 [doi]
• KPC: Learning-Based Model Predictive Control with Deterministic GuaranteesEmilio Tanowe Maddalena, Paul Scharnhorst, Yuning Jiang, Colin N. Jones. 1015-1026 [doi]
• 1-Adaptive Control using Gaussian ProcessesAditya Gahlawat, Arun Lakshmanan, Lin Song, Andrew Patterson, Zhuohuan Wu, Naira Hovakimyan, Evangelos A. Theodorou. 1027-1040 [doi]
• Episodic Learning for Safe Bipedal Locomotion with Control Barrier Functions and Projection-to-State SafetyNoel Csomay-Shanklin, Ryan K. Cosner, Min Dai, Andrew J. Taylor, Aaron D. Ames. 1041-1053 [doi]
• Faster Policy Learning with Continuous-Time GradientsSamuel K. Ainsworth, Kendall Lowrey, John Thickstun, Zaïd Harchaoui, Siddhartha S. Srinivasa. 1054-1067 [doi]
• Learning How to Solve "Bubble Ball"Hotae Lee, Monimoy Bujarbaruah, Francesco Borrelli. 1068-1079 [doi]
• Approximate Midpoint Policy Iteration for Linear Quadratic ControlBenjamin Gravell, Iman Shames, Tyler Summers. 1080-1092 [doi]
• Safe Reinforcement Learning Using Robust Action GovernorYutong Li, Nan Li 0015, H. Eric Tseng, Anouck Girard, Dimitar P. Filev, Ilya V. Kolmanovsky. 1093-1104 [doi]
• SEAGuL: Sample Efficient Adversarially Guided Learning of Value FunctionsBenoit Landry, Hongkai Dai, Marco Pavone. 1105-1117 [doi]
• Fast Stochastic Kalman Gradient Descent for Reinforcement LearningSimone Totaro, Anders Jonsson. 1118-1129 [doi]
• Domain Adaptation Using System Invariant Dynamics ModelsSean J. Wang, Aaron M. Johnson. 1130-1141 [doi]
• Forced Variational Integrator Networks for Prediction and Control of Mechanical SystemsAaron J. Havens, Girish Chowdhary 0001. 1142-1153 [doi]
• Offline Reinforcement Learning from Images with Latent Space ModelsRafael Rafailov, Tianhe Yu, Aravind Rajeswaran, Chelsea Finn. 1154-1168 [doi]
• Adaptive Sampling for Estimating Distributions: A Bayesian Upper Confidence Bound ApproachDhruva Kartik, Neeraj Sood, Urbashi Mitra, Tara Javidi. 1169-1179 [doi]
• A New Objective for Identification of Partially Observed Linear Time-Invariant Dynamical Systems from Input-Output DataNicholas Galioto, Alex Arkady Gorodetsky. 1180-1191 [doi]
• Generating Adversarial Disturbances for Controller VerificationUdaya Ghai, David Snyder, Anirudha Majumdar, Elad Hazan. 1192-1204 [doi]
• Optimal Cost Design for Model Predictive ControlAvik Jain, Lawrence Chan, Daniel S. Brown, Anca D. Dragan. 1205-1217 [doi]
• Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from DataYaofeng Desmond Zhong, Biswadip Dey, Amit Chakraborty. 1218-1229 [doi]
• Learning Visually Guided Latent Actions for Assistive TeleoperationSiddharth Karamcheti, Albert J. Zhai, Dylan P. Losey, Dorsa Sadigh. 1230-1241 [doi]
• Robust Reinforcement Learning: A Constrained Game-theoretic ApproachJing Yu, Clement Gehring, Florian Schäfer, Animashree Anandkumar. 1242-1254 [doi]
• Approximate Distributionally Robust Nonlinear Optimization with Application to Model Predictive Control: A Functional ApproachYassine Nemmour, Bernhard Schölkopf, Jia-Jie Zhu. 1255-1269 [doi]
• Regret-optimal measurement-feedback controlGautam Goel, Babak Hassibi. 1270-1280 [doi]
• Learning Finite-Dimensional Representations For Koopman OperatorsMohammad Khosravi. 1281 [doi]