{"total":116,"rows":[{"id":"2102.08570","title":"Outside the Echo Chamber: Optimizing the Performative Risk","created":"2021-02-17","cited_by_count":96,"area":null},{"id":"2209.05423","title":"Statistical Learning Theory for Control: A Finite Sample Perspective","created":"2022-09-12","cited_by_count":53,"area":null},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2306.12371","title":"Optimistic Active Exploration of Dynamical Systems","created":"2023-06-21","cited_by_count":32,"area":null},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31,"area":null},{"id":"2202.08311","title":"Single Trajectory Nonparametric Learning of Nonlinear Dynamics","created":"2022-02-16","cited_by_count":26,"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":"2106.06098","title":"Meta-Adaptive Nonlinear Control: Theory and Algorithms","created":"2021-06-11","cited_by_count":23,"area":null},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2112.10264","title":"Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models","created":"2021-12-19","cited_by_count":21,"area":null},{"id":"2205.10671","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","created":"2022-05-21","cited_by_count":18,"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":"2102.12661","title":"Online Learning for Unknown Partially Observable MDPs","created":"2021-02-25","cited_by_count":17,"area":null},{"id":"2101.01041","title":"Derivative-Free Policy Optimization for Linear Risk-Sensitive and Robust Control Design: Implicit Regularization and Sample Complexity","created":"2021-01-04","cited_by_count":15,"area":null},{"id":"2102.05214","title":"Task-Optimal Exploration in Linear Dynamical Systems","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2201.11211","title":"Learning Mixtures of Linear Dynamical Systems","created":"2022-01-26","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":"2112.04219","title":"Learning over All Stabilizing Nonlinear Controllers for a Partially-Observed Linear System","created":"2021-12-08","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":"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":"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":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2206.06863","title":"How are policy gradient methods affected by the limits of control?","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2110.06150","title":"Sparsity in Partially Controllable Linear Systems","created":"2021-10-12","cited_by_count":9,"area":null},{"id":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2301.11187","title":"Smoothed Online Learning for Prediction in Piecewise Affine Systems","created":"2023-01-26","cited_by_count":9,"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":"2404.10851","title":"Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens","created":"2024-04-16","cited_by_count":8,"area":"deeprl"},{"id":"2305.15352","title":"Optimal Rates for Bandit Nonstochastic Control","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2404.09030","title":"Active Learning for Control-Oriented Identification of Nonlinear Systems","created":"2024-04-13","cited_by_count":7,"area":"deeprl"},{"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":"2110.07807","title":"Provable Regret Bounds for Deep Online Learning and Control","created":"2021-10-15","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":"2210.04810","title":"Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies","created":"2022-10-10","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":"2311.18736","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","created":"2023-11-30","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":"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":"2106.15775","title":"Koopman Spectrum Nonlinear Regulators and Efficient Online Learning","created":"2021-06-30","cited_by_count":5,"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":"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":"2206.01704","title":"KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems","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":"2302.05430","title":"Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making","created":"2023-02-10","cited_by_count":5,"area":null},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2402.10036","title":"Predictive Linear Online Tracking for Unknown Targets","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2503.24371","title":"Policy Gradient for LQR with Domain Randomization","created":"2025-03-31","cited_by_count":5,"area":"deeprl"},{"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":"2508.11990","title":"Universal Learning of Nonlinear Dynamics","created":"2025-08-16","cited_by_count":5,"area":null},{"id":"2104.00827","title":"How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?","created":"2021-04-02","cited_by_count":4,"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":"2303.16816","title":"PAC-Bayesian bounds for learning LTI-ss systems with input from empirical loss","created":"2023-03-29","cited_by_count":4,"area":null},{"id":"2312.09793","title":"PAC-Bayes Generalisation Bounds for Dynamical Systems Including Stable RNNs","created":"2023-12-15","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":"2105.12358","title":"Certainty Equivalent Quadratic Control for Markov Jump Systems","created":"2021-05-26","cited_by_count":3,"area":null},{"id":"2209.07040","title":"Learning-Based Adaptive Control for Stochastic Linear Systems with Input Constraints","created":"2022-09-15","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":"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":"2502.20030","title":"Offline Reinforcement Learning via Inverse Optimization","created":"2025-02-27","cited_by_count":3,"area":"offlinerl"},{"id":"2505.14821","title":"Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation","created":"2025-05-20","cited_by_count":3,"area":"deeprl"},{"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":"2304.00569","title":"Stability Bounds for Learning-Based Adaptive Control of Discrete-Time Multi-Dimensional Stochastic Linear Systems with Input Constraints","created":"2023-04-02","cited_by_count":2,"area":null},{"id":"2305.10506","title":"Exact Recovery for System Identification with More Corrupt Data than Clean Data","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2401.01258","title":"Model-Free Learning for the Linear Quadratic Regulator over Rate-Limited Channels","created":"2024-01-02","cited_by_count":2,"area":"deeprl"},{"id":"2403.01636","title":"Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks","created":"2024-03-03","cited_by_count":2,"area":"deeprl"},{"id":"2409.08434","title":"Predictive Control and Regret Analysis of Non-Stationary MDP with Look-ahead Information","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2502.19977","title":"Convergence Guarantees of Model-free Policy Gradient Methods for LQR with Stochastic Data","created":"2025-02-27","cited_by_count":2,"area":"deeprl"},{"id":"2510.27428","title":"Learning Soft Robotic Dynamics with Active Exploration","created":"2025-10-31","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":"2111.09434","title":"On the Effectiveness of Iterative Learning Control","created":"2021-11-17","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":"2212.14838","title":"PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models","created":"2022-12-30","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":"2311.02679","title":"Regret Analysis of Learning-Based Linear Quadratic Gaussian Control with Additive Exploration","created":"2023-11-05","cited_by_count":1,"area":null},{"id":"2312.05465","title":"On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR","created":"2023-12-09","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":"2404.08120","title":"A least-square method for non-asymptotic identification in linear switching control","created":"2024-04-11","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":"2602.10971","title":"A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.28938","title":"Optimistic Online LQR via Intrinsic Rewards","created":"2026-03-30","cited_by_count":1,"area":"deeprl"},{"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":"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":"2206.00861","title":"Dynamic Structure Estimation from Bandit Feedback using Nonvanishing Exponential Sums","created":"2022-06-02","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}],"next_cursor":"100"}