{"total":81,"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":"2104.05942","title":"Recurrent Equilibrium Networks: Flexible Dynamic Models with Guaranteed Stability and Robustness","created":"2021-04-13","cited_by_count":45,"area":null},{"id":"2207.05738","title":"PAC Reinforcement Learning for Predictive State Representations","created":"2022-07-12","cited_by_count":43,"area":null},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35,"area":null},{"id":"2102.03758","title":"Non-stationary Online Learning with Memory and Non-stochastic Control","created":"2021-02-07","cited_by_count":33,"area":null},{"id":"2110.06418","title":"Stabilizing Dynamical Systems via Policy Gradient Methods","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21,"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":"2102.05214","title":"Task-Optimal Exploration in Linear Dynamical Systems","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2102.01623","title":"Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory","created":"2021-02-02","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":"2206.12081","title":"Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings","created":"2022-06-24","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":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2104.05087","title":"Learning from Censored and Dependent Data: The case of Linear Dynamics","created":"2021-04-11","cited_by_count":9,"area":null},{"id":"2205.06846","title":"Optimal Comparator Adaptive Online Learning with Switching Cost","created":"2022-05-13","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":"2102.13478","title":"A Regret Minimization Approach to Iterative Learning Control","created":"2021-02-26","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":"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":"2111.00070","title":"Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time","created":"2021-10-29","cited_by_count":6,"area":null},{"id":"2111.06395","title":"Kalman Filtering with Adversarial Corruptions","created":"2021-11-11","cited_by_count":6,"area":null},{"id":"2206.09257","title":"Optimal Dynamic Regret in LQR Control","created":"2022-06-18","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":"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":"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":"2502.06545","title":"Universal Sequence Preconditioning","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2106.10516","title":"DiffLoop: Tuning PID controllers by differentiating through the feedback loop","created":"2021-06-19","cited_by_count":5,"area":null},{"id":"2111.00095","title":"Online Optimization with Feedback Delay and Nonlinear Switching Cost","created":"2021-10-29","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":"2301.00497","title":"Efficient Online Learning with Memory via Frank-Wolfe Optimization: Algorithms with Bounded Dynamic Regret and Applications to Control","created":"2023-01-02","cited_by_count":5,"area":null},{"id":"2302.02426","title":"Online Nonstochastic Control with Adversarial and Static Constraints","created":"2023-02-05","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":"2107.07732","title":"Robust Online Control with Model Misspecification","created":"2021-07-16","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":"2201.13288","title":"A Regret Minimization Approach to Multi-Agent Control","created":"2022-01-28","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":"2301.07902","title":"A Nonstochastic Control Approach to Optimization","created":"2023-01-19","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":"2506.07298","title":"Pre-trained Large Language Models Learn Hidden Markov Models In-context","created":"2025-06-08","cited_by_count":4,"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":"2211.08997","title":"Dynamical Linear Bandits","created":"2022-11-16","cited_by_count":3,"area":null},{"id":"2310.02261","title":"Adaptive Online Non-stochastic Control","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2404.03309","title":"Optimistic Online Non-stochastic Control via FTRL","created":"2024-04-04","cited_by_count":3,"area":null},{"id":"2406.01799","title":"Online Control in Population Dynamics","created":"2024-06-03","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":"2605.09867","title":"Continuous Latent Contexts Enable Efficient Online Learning in Transformers","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2305.17552","title":"Online Nonstochastic Model-Free Reinforcement Learning","created":"2023-05-27","cited_by_count":2,"area":null},{"id":"2410.00993","title":"Tight Rates for Bandit Control Beyond Quadratics","created":"2024-10-01","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":"2205.05119","title":"Robust Data-Driven Output Feedback Control via Bootstrapped Multiplicative Noise","created":"2022-05-10","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":"2403.05786","title":"Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints","created":"2024-03-09","cited_by_count":1,"area":null},{"id":"2406.18805","title":"Online Stackelberg Optimization via Nonlinear Control","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2506.01226","title":"React to Surprises: Stable-by-Design Neural Feedback Control and the Youla-REN","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2101.10357","title":"Regret-Optimal Filtering for Prediction and Estimation","created":"2021-01-25","cited_by_count":0,"area":null},{"id":"2305.00154","title":"Learning to Seek: Multi-Agent Online Source Seeking Against Non-Stochastic Disturbances","created":"2023-04-29","cited_by_count":0,"area":null},{"id":"2308.08138","title":"Data-Driven Adversarial Online Control for Unknown Linear Systems","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2402.10252","title":"Online Control of Linear Systems under Unbounded Noise","created":"2024-02-15","cited_by_count":0,"area":null},{"id":"2403.05899","title":"Online Identification of Stochastic Continuous-Time Wiener Models Using Sampled Data","created":"2024-03-09","cited_by_count":0,"area":null},{"id":"2403.08553","title":"Regret Analysis of Policy Optimization over Submanifolds for Linearly Constrained Online LQG","created":"2024-03-13","cited_by_count":0,"area":null},{"id":"2407.11471","title":"Safe Online Convex Optimization with Multi-Point Feedback","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2410.23574","title":"Online Convex Optimization with Memory and Limited Predictions","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2501.04572","title":"Regret Analysis: a control perspective","created":"2025-01-08","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":"2506.18814","title":"Online Multi-Agent Control with Adversarial Disturbances","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2601.09042","title":"SCaLE: Switching Cost aware Learning and Exploration","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2605.04364","title":"Online Nonstochastic Prediction: Logarithmic Regret via Predictive Online Least Squares","created":"2026-05-06","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":"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}