{"total":29,"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":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2212.00603","title":"Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP","created":"2022-12-01","cited_by_count":29,"area":null},{"id":"2110.06418","title":"Stabilizing Dynamical Systems via Policy Gradient Methods","created":"2021-10-13","cited_by_count":25,"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":"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":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"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":"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":"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":"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":"2311.18736","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","created":"2023-11-30","cited_by_count":6,"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":"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":"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":"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":"2210.08886","title":"Learning Decentralized Linear Quadratic Regulators with $\\sqrt{T}$ Regret","created":"2022-10-17","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":"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":"2102.06258","title":"Using Echo State Networks to Approximate Value Functions for Control","created":"2021-02-11","cited_by_count":0,"area":null},{"id":"2112.04101","title":"Learning Linear Models Using Distributed Iterative Hessian Sketching","created":"2021-12-08","cited_by_count":0,"area":null},{"id":"2204.01925","title":"Online No-regret Model-Based Meta RL for Personalized Navigation","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2303.16548","title":"Policy Gradient Methods for Discrete Time Linear Quadratic Regulator With Random Parameters","created":"2023-03-29","cited_by_count":0,"area":null},{"id":"2309.16291","title":"Efficiency Separation between RL Methods: Model-Free, Model-Based and Goal-Conditioned","created":"2023-09-28","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":"2509.23620","title":"Communication-aware Wide-Area Damping Control using Risk-Constrained Reinforcement Learning","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2604.14484","title":"Behavior Cloning Under PD Control: A Finite-Horizon Theory of Gain-Dependent Error Amplification","created":"2026-04-15","cited_by_count":0,"area":null}],"next_cursor":null}