{"total":70,"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":"2110.06418","title":"Stabilizing Dynamical Systems via Policy Gradient Methods","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2306.09210","title":"Optimal Exploration for Model-Based RL in Nonlinear Systems","created":"2023-06-15","cited_by_count":18,"area":null},{"id":"2102.03803","title":"Lazy OCO: Online Convex Optimization on a Switching Budget","created":"2021-02-07","cited_by_count":14,"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":"2308.14642","title":"Rate-Optimal Policy Optimization for Linear Markov Decision Processes","created":"2023-08-28","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":"2102.12608","title":"Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\\sqrt{T}$ Regret","created":"2021-02-25","cited_by_count":12,"area":null},{"id":"2407.17226","title":"Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems","created":"2024-07-24","cited_by_count":12,"area":"deeprl"},{"id":"2502.13900","title":"Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning","created":"2025-02-19","cited_by_count":12,"area":"offlinerl"},{"id":"2201.01680","title":"Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems","created":"2022-01-05","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":"2405.07637","title":"Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback","created":"2024-05-13","cited_by_count":10,"area":"deeprl"},{"id":"2110.06150","title":"Sparsity in Partially Controllable Linear Systems","created":"2021-10-12","cited_by_count":9,"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":"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":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"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":"2208.04466","title":"Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning","created":"2022-08-08","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":"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":"2402.03792","title":"No-Regret Reinforcement Learning in Smooth MDPs","created":"2024-02-06","cited_by_count":6,"area":"deeprl"},{"id":"2501.15910","title":"The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective","created":"2025-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2502.06545","title":"Universal Sequence Preconditioning","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2108.02307","title":"Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function","created":"2021-08-04","cited_by_count":5,"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":"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":"2405.06363","title":"Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs","created":"2024-05-10","cited_by_count":5,"area":"deeprl"},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"id":"2505.03706","title":"Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches","created":"2025-05-06","cited_by_count":5,"area":"deeprl"},{"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":"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":"2406.01175","title":"NeoRL: Efficient Exploration for Nonepisodic RL","created":"2024-06-03","cited_by_count":4,"area":"deeprl"},{"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":"2410.24071","title":"Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs","created":"2024-10-31","cited_by_count":4,"area":"deeprl"},{"id":"2111.15041","title":"Online Learning for Predictive Control with Provable Regret Guarantees","created":"2021-11-30","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":"2206.01782","title":"Optimal Competitive-Ratio Control","created":"2022-06-03","cited_by_count":2,"area":null},{"id":"2309.02815","title":"Near-continuous time Reinforcement Learning for continuous state-action spaces","created":"2023-09-06","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":"2406.00234","title":"Learning to Stabilize Unknown LTI Systems on a Single Trajectory under Stochastic Noise","created":"2024-05-31","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":"2505.01041","title":"Global Optimality of Single-Timescale Actor-Critic under Continuous State-Action Space: A Study on Linear Quadratic Regulator","created":"2025-05-02","cited_by_count":2,"area":"deeprl"},{"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":"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":"2403.05367","title":"Stability-Certified On-Policy Data-Driven LQR via Recursive Learning and Policy Gradient","created":"2024-03-08","cited_by_count":1,"area":"deeprl"},{"id":"2403.05786","title":"Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2405.17370","title":"Model-Agnostic Zeroth-Order Policy Optimization for Meta-Learning of Ergodic Linear Quadratic Regulators","created":"2024-05-27","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":"2601.19284","title":"Model-Free Output Feedback Stabilization via Policy Gradient Methods","created":"2026-01-27","cited_by_count":1,"area":"deeprl"},{"id":"2602.22810","title":"Multi-agent imitation learning with function approximation: Linear Markov games and beyond","created":"2026-02-26","cited_by_count":1,"area":"offlinerl"},{"id":"2603.28938","title":"Optimistic Online LQR via Intrinsic Rewards","created":"2026-03-30","cited_by_count":1,"area":"deeprl"},{"id":"2101.10357","title":"Regret-Optimal Filtering for Prediction and Estimation","created":"2021-01-25","cited_by_count":0,"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":"2206.02507","title":"Learning to Control under Time-Varying Environment","created":"2022-06-06","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":"2505.20943","title":"Efficient Spectral Control of Partially Observed Linear Dynamical Systems","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2601.03016","title":"Adaptive Control of Unknown Linear Switched Systems via Policy Gradient Methods","created":"2026-01-06","cited_by_count":0,"area":"deeprl"},{"id":"2607.16895","title":"When Can Safe Controllers Adapt? Information before Commitment","created":"2026-07-18","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}