{"total":78,"rows":[{"id":"2209.05423","title":"Statistical Learning Theory for Control: A Finite Sample Perspective","created":"2022-09-12","cited_by_count":53,"area":null},{"id":"2104.14074","title":"Statistical Inference with M-Estimators on Adaptively Collected Data","created":"2021-04-29","cited_by_count":40,"area":null},{"id":"2110.06418","title":"Stabilizing Dynamical Systems via Policy Gradient Methods","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2104.09311","title":"Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls","created":"2021-04-19","cited_by_count":24,"area":null},{"id":"2303.10506","title":"Neural Operators of Backstepping Controller and Observer Gain Functions for Reaction-Diffusion PDEs","created":"2023-03-18","cited_by_count":18,"area":null},{"id":"2102.12661","title":"Online Learning for Unknown Partially Observable MDPs","created":"2021-02-25","cited_by_count":17,"area":null},{"id":"2102.05214","title":"Task-Optimal Exploration in Linear Dynamical Systems","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2107.07410","title":"PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration","created":"2021-07-15","cited_by_count":14,"area":null},{"id":"2111.07018","title":"Identification and Adaptive Control of Markov Jump Systems: Sample Complexity and Regret Bounds","created":"2021-11-13","cited_by_count":14,"area":null},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2202.07890","title":"Online Control of Unknown Time-Varying Dynamical Systems","created":"2022-02-16","cited_by_count":13,"area":null},{"id":"2308.04428","title":"Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data","created":"2023-08-08","cited_by_count":13,"area":null},{"id":"2208.13915","title":"Finite Sample Identification of Bilinear Dynamical Systems","created":"2022-08-29","cited_by_count":12,"area":null},{"id":"2111.00411","title":"Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees","created":"2021-10-31","cited_by_count":11,"area":null},{"id":"2201.01680","title":"Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems","created":"2022-01-05","cited_by_count":11,"area":null},{"id":"2205.14035","title":"Learning to Control Linear Systems can be Hard","created":"2022-05-27","cited_by_count":11,"area":null},{"id":"2106.12097","title":"Regret-optimal Estimation and Control","created":"2021-06-22","cited_by_count":10,"area":null},{"id":"2102.13478","title":"A Regret Minimization Approach to Iterative Learning Control","created":"2021-02-26","cited_by_count":8,"area":null},{"id":"2206.08520","title":"Thompson Sampling Achieves $\\tilde O(\\sqrt{T})$ Regret in Linear Quadratic Control","created":"2022-06-17","cited_by_count":8,"area":null},{"id":"2208.08744","title":"Global Convergence of Two-timescale Actor-Critic for Solving Linear Quadratic Regulator","created":"2022-08-18","cited_by_count":8,"area":null},{"id":"2302.04344","title":"Learning Dynamical Systems by Leveraging Data from Similar Systems","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2104.08261","title":"Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertainty","created":"2021-04-16","cited_by_count":7,"area":null},{"id":"2110.07112","title":"On the Sample Complexity of Decentralized Linear Quadratic Regulator with Partially Nested Information Structure","created":"2021-10-14","cited_by_count":7,"area":null},{"id":"2305.15352","title":"Optimal Rates for Bandit Nonstochastic Control","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2105.07310","title":"Regret Analysis of Distributed Online LQR Control for Unknown LTI Systems","created":"2021-05-15","cited_by_count":6,"area":null},{"id":"2110.07807","title":"Provable Regret Bounds for Deep Online Learning and Control","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2210.09903","title":"Online Convex Optimization with Unbounded Memory","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2211.11219","title":"Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret","created":"2022-11-21","cited_by_count":6,"area":null},{"id":"2309.14648","title":"Learning the Uncertainty Sets for Control Dynamics via Set Membership: A Non-Asymptotic Analysis","created":"2023-09-26","cited_by_count":6,"area":null},{"id":"2310.01706","title":"On Representation Complexity of Model-based and Model-free Reinforcement Learning","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2401.00073","title":"Nonasymptotic Regret Analysis of Adaptive Linear Quadratic Control with Model Misspecification","created":"2023-12-29","cited_by_count":6,"area":null},{"id":"2409.16499","title":"Learning Linear Dynamics from Bilinear Observations","created":"2024-09-24","cited_by_count":6,"area":null},{"id":"2502.06545","title":"Universal Sequence Preconditioning","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2112.14195","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","created":"2021-12-28","cited_by_count":5,"area":null},{"id":"2201.10542","title":"Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems","created":"2022-01-25","cited_by_count":5,"area":null},{"id":"2206.01426","title":"Rate-Optimal Online Convex Optimization in Adaptive Linear Control","created":"2022-06-03","cited_by_count":5,"area":null},{"id":"2208.10259","title":"Meta-Learning Online Control for Linear Dynamical Systems","created":"2022-08-18","cited_by_count":5,"area":null},{"id":"2306.10369","title":"Non-asymptotic System Identification for Linear Systems with Nonlinear Policies","created":"2023-06-17","cited_by_count":5,"area":null},{"id":"2501.07652","title":"Finite Sample Identification of Partially Observed Bilinear Dynamical Systems","created":"2025-01-13","cited_by_count":5,"area":null},{"id":"2108.11959","title":"Finite-time System Identification and Adaptive Control in Autoregressive Exogenous Systems","created":"2021-08-26","cited_by_count":4,"area":null},{"id":"2111.03772","title":"Dynamic Regret Minimization for Control of Non-stationary Linear Dynamical Systems","created":"2021-11-06","cited_by_count":4,"area":null},{"id":"2203.01170","title":"Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics","created":"2022-03-02","cited_by_count":4,"area":null},{"id":"2309.02476","title":"Optimal Sample Selection Through Uncertainty Estimation and Its Application in Deep Learning","created":"2023-09-05","cited_by_count":4,"area":null},{"id":"2312.12558","title":"Sample Efficient Reinforcement Learning with Partial Dynamics Knowledge","created":"2023-12-19","cited_by_count":4,"area":null},{"id":"2407.05781","title":"Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2104.14134","title":"Stable Online Control of Linear Time-Varying Systems","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2105.06577","title":"Online Algorithms and Policies Using Adaptive and Machine Learning Approaches","created":"2021-05-13","cited_by_count":3,"area":null},{"id":"2111.15041","title":"Online Learning for Predictive Control with Provable Regret Guarantees","created":"2021-11-30","cited_by_count":3,"area":null},{"id":"2211.07411","title":"Implications of Regret on Stability of Linear Dynamical Systems","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2304.06783","title":"A Distributionally Robust Approach to Regret Optimal Control using the Wasserstein Distance","created":"2023-04-13","cited_by_count":3,"area":null},{"id":"2406.00574","title":"On the Sample Complexity of Set Membership Estimation for Linear Systems with Disturbances Bounded by Convex Sets","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2407.11069","title":"Combining Federated Learning and Control: A Survey","created":"2024-07-12","cited_by_count":3,"area":null},{"id":"2108.07970","title":"Scalable regret for learning to control network-coupled subsystems with unknown dynamics","created":"2021-08-18","cited_by_count":2,"area":null},{"id":"2311.00181","title":"Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization","created":"2023-10-31","cited_by_count":2,"area":null},{"id":"2502.04649","title":"End-to-End Learning Framework for Solving Non-Markovian Optimal Control","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2504.03952","title":"A New Approach to Controlling Linear Dynamical Systems","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2510.16208","title":"Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2108.08502","title":"A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems","created":"2021-08-19","cited_by_count":1,"area":null},{"id":"2210.08886","title":"Learning Decentralized Linear Quadratic Regulators with $\\sqrt{T}$ Regret","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2212.01371","title":"Adaptive Robust Model Predictive Control via Uncertainty Cancellation","created":"2022-12-02","cited_by_count":1,"area":null},{"id":"2212.08949","title":"Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2301.07876","title":"Suboptimality analysis of receding horizon quadratic control with unknown linear systems and its applications in learning-based control","created":"2023-01-19","cited_by_count":1,"area":null},{"id":"2310.03206","title":"Regret Analysis of Distributed Online Control for LTI Systems with Adversarial Disturbances","created":"2023-10-04","cited_by_count":1,"area":null},{"id":"2311.11151","title":"On the Hardness of Learning to Stabilize Linear Systems","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2311.18769","title":"Online Change Points Detection for Linear Dynamical Systems with Finite Sample Guarantees","created":"2023-11-30","cited_by_count":1,"area":null},{"id":"2511.05444","title":"Adversarially Robust Multitask Adaptive Control","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2103.13278","title":"Safe Linear-Quadratic Dual Control with Almost Sure Performance Guarantee","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2105.01244","title":"Regret-Optimal LQR Control","created":"2021-05-04","cited_by_count":0,"area":null},{"id":"2202.05799","title":"Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics","created":"2022-02-11","cited_by_count":0,"area":null},{"id":"2301.05537","title":"Almost Surely $\\sqrt{T}$ Regret for Adaptive LQR","created":"2023-01-13","cited_by_count":0,"area":null},{"id":"2305.16974","title":"Finite Time Regret Bounds for Minimum Variance Control of Autoregressive Systems with Exogenous Inputs","created":"2023-05-26","cited_by_count":0,"area":null},{"id":"2411.15972","title":"Stability properties of gradient flow dynamics for the symmetric low-rank matrix factorization problem","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2412.04157","title":"Non-Asymptotic Bounds for Closed-Loop Identification of Sub-Exponentially Growing Nonlinear Stochastic Systems","created":"2024-12-05","cited_by_count":0,"area":null},{"id":"2505.20943","title":"Efficient Spectral Control of Partially Observed Linear Dynamical Systems","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2605.10493","title":"A PAC-Bayes Approach for Controlling Unknown Linear Discrete-time Systems","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2608.02375","title":"A Spectral Filtering Approach to Regret Analysis of Distributed Online Control for Linear Dynamical Systems","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.13651","title":"Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2610.00911","title":"Block Optimism for Nonstationary Bandits with Latent Linear Dynamics","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}