Abstract is missing.
- Preface1-4 [doi]
- Actively Learning Gaussian Process DynamicsMona Buisson-Fenet, Friedrich Solowjow, Sebastian Trimpe. 5-15 [doi]
- Finite Sample System Identification: Optimal Rates and the Role of RegularizationYue Sun, Samet Oymak, Maryam Fazel. 16-25 [doi]
- Finite-Time Performance of Distributed Two-Time-Scale Stochastic ApproximationThinh T. Doan, Justin Romberg. 26-36 [doi]
- Virtual Reference Feedback Tuning with data-driven reference model selectionValentina Breschi, Simone Formentin. 37-45 [doi]
- Direct Data-Driven Control with Embedded Anti-Windup CompensationValentina Breschi, Simone Formentin. 46-54 [doi]
- Sparse and Low-bias Estimation of High Dimensional Vector Autoregressive ModelsTrevor Ruiz, Sharmodeep Bhattacharyya, Mahesh Balasubramanian 0001, Kristofer E. Bouchard. 55-64 [doi]
- Robust Online Model Adaptation by Extended Kalman Filter with Exponential Moving Average and Dynamic Multi-Epoch StrategyAbulikemu Abuduweili, Changliu Liu. 65-74 [doi]
- Estimating Reachable Sets with Scenario OptimizationAlex Devonport, Murat Arcak. 75-84 [doi]
- LSTM Neural Networks: Input to State Stability and Probabilistic Safety VerificationFabio Bonassi, Enrico Terzi, Marcello Farina, Riccardo Scattolini. 85-94 [doi]
- Bayesian joint state and parameter tracking in autoregressive modelsIsmail Senöz, Albert Podusenko, Wouter M. Kouw, Bert de Vries. 95-104 [doi]
- Learning to Correspond Dynamical SystemsNam-Hee Kim, Zhaoming Xie, Michiel van de Panne. 105-117 [doi]
- Learning solutions to hybrid control problems using Benders cutsSandeep Menta, Joseph Warrington, John Lygeros, Manfred Morari. 118-126 [doi]
- Feed-forward Neural Networks with Trainable DelayXunbi A. Ji, Tamás G. Molnár, Sergei S. Avedisov, Gábor Orosz. 127-136 [doi]
- Exploiting Model Sparsity in Adaptive MPC: A Compressed Sensing ViewpointMonimoy Bujarbaruah, Charlott Vallon. 137-146 [doi]
- Structured Variational Inference in Partially Observable UnstableGaussian Process State Space ModelsSebastian Curi, Silvan Melchior, Felix Berkenkamp, Andreas Krause. 147-157 [doi]
- Regret Bound for Safe Gaussian Process Bandit OptimizationSanae Amani, Mahnoosh Alizadeh, Christos Thrampoulidis. 158-159 [doi]
- Smart Forgetting for Safe Online Learning with Gaussian ProcessesJonas Umlauft, Thomas Beckers, Alexandre Capone, Armin Lederer, Sandra Hirche. 160-169 [doi]
- Linear Antisymmetric Recurrent Neural NetworksSigne Moe, Filippo Remonato, Esten Ingar Grøtli, Jan Tommy Gravdahl. 170-178 [doi]
- ∞ Robustness Guarantee: Implicit Regularization and Global ConvergenceKaiqing Zhang, Bin Hu, Tamer Basar. 179-190 [doi]
- A Finite-Sample Deviation Bound for Stable Autoregressive ProcessesRodrigo A. González, Cristian R. Rojas. 191-200 [doi]
- Online Data Poisoning AttacksXuezhou Zhang, Xiaojin Zhu 0001, Laurent Lessard. 201-210 [doi]
- Practical Reinforcement Learning For MPC: Learning from sparse objectives in under an hour on a real robotNapat Karnchanachari, Miguel de la Iglesia Valls, David Hoeller, Marco Hutter 0001. 211-224 [doi]
- Learning Constrained Dynamics with Gauss' Principle adhering Gaussian ProcessesAndreas Rene Geist, Sebastian Trimpe. 225-234 [doi]
- Counterfactual Programming for Optimal ControlLuiz F. O. Chamon, Santiago Paternain, Alejandro Ribeiro. 235-244 [doi]
- Learning Navigation Costs from Demonstrations with Semantic ObservationsTianyu Wang, Vikas Dhiman, Nikolay Atanasov. 245-255 [doi]
- Scalable Reinforcement Learning of Localized Policies for Multi-Agent Networked SystemsGuannan Qu, Adam Wierman, Na Li 0002. 256-266 [doi]
- Black-box continuous-time transfer function estimation with stability guarantees: a kernel-based approachMirko Mazzoleni, Matteo Scandella, Simone Formentin, Fabio Previdi. 267-276 [doi]
- Model-Predictive Control via Cross-Entropy and Gradient-Based OptimizationHomanga Bharadhwaj, Kevin Xie, Florian Shkurti. 277-286 [doi]
- Learning the Globally Optimal Distributed LQ RegulatorLuca Furieri, Yang Zheng 0001, Maryam Kamgarpour. 287-297 [doi]
- VarNet: Variational Neural Networks for the Solution of Partial Differential EquationsReza Khodayi-mehr, Michael M. Zavlanos. 298-307 [doi]
- Tractable Reinforcement Learning of Signal Temporal Logic ObjectivesHarish K. Venkataraman, Derya Aksaray, Peter J. Seiler. 308-317 [doi]
- A Spatially and Temporally Attentive Joint Trajectory Prediction Framework for Modeling Vessel IntentJasmine Sekhon, Cody Fleming. 318-327 [doi]
- Structured Mechanical Models for Robot Learning and ControlJayesh K. Gupta, Kunal Menda, Zachary Manchester, Mykel J. Kochenderfer. 328-337 [doi]
- Data-driven Identification of Approximate Passive Linear Models for Nonlinear SystemsSivaranjani S., Etika Agarwal, Vijay Gupta 0001. 338-339 [doi]
- Constraint Management for Batch Processes Using Iterative Learning Control and Reference GovernorsAidan Laracy, Hamid R. Ossareh. 340-349 [doi]
- Robust Guarantees for Perception-Based ControlSarah Dean, Nikolai Matni, Benjamin Recht, Vickie Ye. 350-360 [doi]
- Learning Convex Optimization Control PoliciesAkshay Agrawal, Shane T. Barratt, Stephen P. Boyd, Bartolomeo Stellato. 361-373 [doi]
- Fitting a Linear Control Policy to Demonstrations with a Kalman ConstraintMalayandi Palan, Shane T. Barratt, Alex McCauley, Dorsa Sadigh, Vikas Sindhwani, Stephen P. Boyd. 374-383 [doi]
- Universal Simulation of Stable Dynamical Systems by Recurrent Neural NetsJoshua Hanson, Maxim Raginsky. 384-392 [doi]
- Contracting Implicit Recurrent Neural Networks: Stable Models with Improved TrainabilityMax Revay, Ian R. Manchester. 393-403 [doi]
- On the Robustness of Data-Driven Controllers for Linear SystemsAnguluri Rajasekhar, Abed AlRahman Al Makdah, Vaibhav Katewa, Fabio Pasqualetti. 404-412 [doi]
- Faster saddle-point optimization for solving large-scale Markov decision processesJoan Bas-Serrano, Gergely Neu. 413-423 [doi]
- On Simulation and Trajectory Prediction with Gaussian Process DynamicsLukas Hewing, Elena Arcari, Lukas P. Fröhlich, Melanie N. Zeilinger. 424-434 [doi]
- Sample Complexity of Kalman Filtering for Unknown SystemsAnastasios Tsiamis, Nikolai Matni, George J. Pappas. 435-444 [doi]
- NeurOpt: Neural network based optimization for building energy management and climate controlAchin Jain, Francesco Smarra, Enrico Reticcioli, Alessandro D'Innocenzo, Manfred Morari. 445-454 [doi]
- Bayesian model predictive control: Efficient model exploration and regret bounds using posterior samplingKim Peter Wabersich, Melanie N. Zeilinger. 455-464 [doi]
- Parameter Optimization for Learning-based Control of Control-Affine SystemsArmin Lederer, Alexandre Capone, Sandra Hirche. 465-475 [doi]
- Riccati updates for online linear quadratic controlMohammad Akbari 0002, Bahman Gharesifard, Tamás Linder. 476-485 [doi]
- A Theoretical Analysis of Deep Q-LearningJianqing Fan, Zhaoran Wang, Yuchen Xie, Zhuoran Yang. 486-489 [doi]
- Localized active learning of Gaussian process state space modelsAlexandre Capone, Gerrit Noske, Jonas Umlauft, Thomas Beckers, Armin Lederer, Sandra Hirche. 490-499 [doi]
- Generating Robust Supervision for Learning-Based Visual Navigation Using Hamilton-Jacobi ReachabilityAnjian Li, Somil Bansal, Georgios Giovanis, Varun Tolani, Claire J. Tomlin, Mo Chen. 500-510 [doi]
- Learning supported Model Predictive Control for Tracking of Periodic ReferencesJanine Matschek, Rolf Findeisen. 511-520 [doi]
- Data-driven distributionally robust LQR with multiplicative noisePeter Coppens, Mathijs Schuurmans, Panagiotis Patrinos. 521-530 [doi]
- Learning the model-free linear quadratic regulator via random searchHesameddin Mohammadi, Mihailo R. Jovanovic, Mahdi Soltanolkotabi. 531-539 [doi]
- Lambda-Policy Iteration with Randomization for Contractive Models with Infinite Policies: Well-Posedness and ConvergenceYuchao Li, Karl Henrik Johansson, Jonas Mårtensson. 540-549 [doi]
- Optimistic robust linear quadratic dual controlJack Umenberger, Thomas B. Schön. 550-560 [doi]
- Bayesian Learning with Adaptive Load Allocation StrategiesManxi Wu, Saurabh Amin, Asuman E. Ozdaglar. 561-570 [doi]
- Learning-based Stochastic Model Predictive Control with State-Dependent UncertaintyAngelo Domenico Bonzanini, Ali Mesbah 0002. 571-580 [doi]
- Stable Reinforcement Learning with Unbounded State SpaceDevavrat Shah, Qiaomin Xie, Zhi Xu. 581 [doi]
- Periodic Q-LearningDonghwan Lee 0002, Niao He. 582-598 [doi]
- Robust Learning-Based Control via Bootstrapped Multiplicative NoiseBenjamin Gravell, Tyler Summers. 599-607 [doi]
- Robust Regression for Safe Exploration in ControlAnqi Liu, Guanya Shi, Soon Jo Chung, Anima Anandkumar, Yisong Yue. 608-619 [doi]
- Constrained Upper Confidence Reinforcement LearningLiyuan Zheng, Lillian J. Ratliff. 620-629 [doi]
- Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical SystemsMuhammad Asif Rana, Anqi Li, Dieter Fox, Byron Boots, Fabio Ramos, Nathan D. Ratliff. 630-639 [doi]
- Planning from Images with Deep Latent Gaussian Process DynamicsNathanael Bosch, Jan Achterhold, Laura Leal-Taixé, Jörg Stückler. 640-650 [doi]
- A First Principles Approach for Data-Efficient System Identification of Spring-Rod Systems via Differentiable Physics EnginesKun Wang, Mridul Aanjaneya, Kostas E. Bekris. 651-665 [doi]
- Model-Based Reinforcement Learning with Value-Targeted RegressionZeyu Jia, Lin Yang, Csaba Szepesvári, Mengdi Wang. 666-686 [doi]
- Localized Learning of Robust Controllers for Networked Systems with Dynamic TopologySooJean Han. 687-696 [doi]
- NeuralExplorer: State Space Exploration of Closed Loop Control Systems Using Neural NetworksManish Goyal 0002, Parasara Sridhar Duggirala. 697 [doi]
- Toward fusion plasma scenario planning for NSTX-U using machine-learning-accelerated modelsMark Boyer. 698-707 [doi]
- Learning for Safety-Critical Control with Control Barrier FunctionsAndrew J. Taylor, Andrew Singletary, Yisong Yue, Aaron D. Ames. 708-717 [doi]
- Learning Dynamical Systems with Side InformationAmir Ali Ahmadi, Bachir El Khadir. 718-727 [doi]
- Feynman-Kac Neural Network Architectures for Stochastic Control Using Second-Order FBSDE TheoryMarcus Pereira, Ziyi Wang, Tianrong Chen, Emily A. Reed, Evangelos A. Theodorou. 728-738 [doi]
- Hamilton-Jacobi-Bellman Equations for Q-Learning in Continuous TimeJeongho Kim, Insoon Yang. 739-748 [doi]
- Identifying Mechanical Models of Unknown Objects with Differentiable Physics SimulationsChangkyu Song, Abdeslam Boularias. 749-760 [doi]
- Objective Mismatch in Model-based Reinforcement LearningNathan O. Lambert, Brandon Amos, Omry Yadan, Roberto Calandra. 761-770 [doi]
- Tools for Data-driven Modeling of Within-Hand Manipulation with Underactuated Adaptive HandsAvishai Sintov, Andrew Kimmel, Bowen Wen, Abdeslam Boularias, Kostas E. Bekris. 771-780 [doi]
- Probabilistic Safety Constraints for Learned High Relative Degree System DynamicsMohammad Javad Khojasteh, Vikas Dhiman, Massimo Franceschetti, Nikolay Atanasov. 781-792 [doi]
- Lyceum: An efficient and scalable ecosystem for robot learningColin Summers, Kendall Lowrey, Aravind Rajeswaran, Siddhartha S. Srinivasa, Emanuel Todorov. 793-803 [doi]
- Encoding Physical Constraints in Differentiable Newton-Euler AlgorithmGiovanni Sutanto, Austin Wang, Yixin Lin, Mustafa Mukadam, Gaurav S. Sukhatme, Akshara Rai, Franziska Meier. 804-813 [doi]
- Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization ApproachYingying Li, Yujie Tang, Runyu Zhang, Na Li. 814 [doi]
- Learning to Plan via Deep Optimistic Value ExplorationTim Seyde, Wilko Schwarting, Sertac Karaman, Daniela Rus. 815-825 [doi]
- L1-GP: L1 Adaptive Control with Bayesian LearningAditya Gahlawat, Pan Zhao, Andrew Patterson, Naira Hovakimyan, Evangelos A. Theodorou. 826-837 [doi]
- Data-Driven Distributed Predictive Control via Network OptimizationAhmed Allibhoy, Jorge Cortés. 838-839 [doi]
- Information Theoretic Model Predictive Q-LearningMohak Bhardwaj, Ankur Handa, Dieter Fox, Byron Boots. 840-850 [doi]
- Learning nonlinear dynamical systems from a single trajectoryDylan J. Foster, Tuhin Sarkar, Alexander Rakhlin. 851-861 [doi]
- A Duality Approach for Regret Minimization in Average-Award Ergodic Markov Decision ProcessesHao Gong, Mengdi Wang. 862-883 [doi]
- Robust Deep Learning as Optimal Control: Insights and Convergence GuaranteesJacob H. Seidman, Mahyar Fazlyab, Victor M. Preciado, George J. Pappas. 884-893 [doi]
- Dual Stochastic MPC for Systems with Parametric and Structural UncertaintyElena Arcari, Lukas Hewing, Max Schlichting, Melanie N. Zeilinger. 894-903 [doi]
- Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy DistillationHany Abdulsamad, Jan Peters 0001. 904-914 [doi]
- A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and ControlJia-Jie Zhu, Bernhard Schölkopf, Moritz Diehl. 915-923 [doi]
- Efficient Large-Scale Gaussian Process Bandits by Believing only Informative ActionsAmrit Singh Bedi, Dheeraj Peddireddy, Vaneet Aggarwal, Alec Koppel. 924-934 [doi]
- Plan2Vec: Unsupervised Representation Learning by Latent PlansGe Yang, Amy Zhang 0001, Ari S. Morcos, Joelle Pineau, Pieter Abbeel, Roberto Calandra. 935-946 [doi]
- Policy Learning of MDPs with Mixed Continuous/Discrete Variables: A Case Study on Model-Free Control of Markovian Jump SystemsJoao Paulo Jansch-Porto, Bin Hu, Geir E. Dullerud. 947-957 [doi]
- Improving Robustness via Risk Averse Distributional Reinforcement LearningRahul Singh, Qinsheng Zhang, Yongxin Chen. 958-968 [doi]
- Keyframing the Future: Keyframe Discovery for Visual Prediction and PlanningKarl Pertsch, Oleh Rybkin, Jingyun Yang, Shenghao Zhou, Konstantinos G. Derpanis, Kostas Daniilidis, Joseph J. Lim, Andrew Jaegle. 969-979 [doi]
- Safe non-smooth black-box optimization with application to policy searchIlnura Usmanova, Andreas Krause 0001, Maryam Kamgarpour. 980-989 [doi]
- Improving Input-Output Linearizing Controllers for Bipedal Robots via Reinforcement LearningFernando Castañeda, Mathias Wulfman, Ayush Agrawal, Tyler Westenbroek, Shankar Sastry, Claire J. Tomlin, Koushil Sreenath. 990-999 [doi]
- Uncertain multi-agent MILPs: A data-driven decentralized solution with probabilistic feasibility guaranteesAlessandro Falsone, Federico Molinari, Maria Prandini. 1000-1009 [doi]