{"total":161,"rows":[{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223,"area":null},{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89,"area":null},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84,"area":null},{"id":"2107.11433","title":"A general sample complexity analysis of vanilla policy gradient","created":"2021-07-23","cited_by_count":76,"area":null},{"id":"2102.08607","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","created":"2021-02-17","cited_by_count":70,"area":null},{"id":"2211.07937","title":"An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods","created":"2022-11-15","cited_by_count":68,"area":null},{"id":"2302.01734","title":"Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies","created":"2023-02-03","cited_by_count":58,"area":null},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53,"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":"2112.05604","title":"Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity","created":"2021-12-10","cited_by_count":49,"area":null},{"id":"2102.11270","title":"Softmax Policy Gradient Methods Can Take Exponential Time to Converge","created":"2021-02-22","cited_by_count":48,"area":null},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46,"area":null},{"id":"2301.00712","title":"On Finding Small Hyper-Gradients in Bilevel Optimization: Hardness Results and Improved Analysis","created":"2023-01-02","cited_by_count":39,"area":null},{"id":"2210.09921","title":"Finite-time analysis of single-timescale actor-critic","created":"2022-10-18","cited_by_count":32,"area":null},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2110.10116","title":"On the Global Optimum Convergence of Momentum-based Policy Gradient","created":"2021-10-19","cited_by_count":26,"area":null},{"id":"2107.13090","title":"Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games","created":"2021-07-27","cited_by_count":25,"area":null},{"id":"2110.06418","title":"Stabilizing Dynamical Systems via Policy Gradient Methods","created":"2021-10-13","cited_by_count":25,"area":null},{"id":"2211.00617","title":"Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems","created":"2022-11-01","cited_by_count":25,"area":null},{"id":"2109.14756","title":"A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning","created":"2021-09-29","cited_by_count":24,"area":null},{"id":"2303.10257","title":"Recent Developments in Machine Learning Methods for Stochastic Control and Games","created":"2023-03-17","cited_by_count":24,"area":null},{"id":"2310.02951","title":"A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2208.11639","title":"Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path","created":"2022-08-24","cited_by_count":20,"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":"2110.11383","title":"Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes","created":"2021-10-21","cited_by_count":17,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2312.12065","title":"PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping","created":"2023-12-19","cited_by_count":17,"area":null},{"id":"2109.03861","title":"Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems","created":"2021-09-08","cited_by_count":16,"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":"2201.11211","title":"Learning Mixtures of Linear Dynamical Systems","created":"2022-01-26","cited_by_count":15,"area":null},{"id":"2202.00048","title":"Single Time-scale Actor-critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees","created":"2022-01-31","cited_by_count":14,"area":null},{"id":"2307.11782","title":"Convergence of Adam for Non-convex Objectives: Relaxed Hyperparameters and Non-ergodic Case","created":"2023-07-20","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":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2112.10935","title":"Nearly Optimal Policy Optimization with Stable at Any Time Guarantee","created":"2021-12-21","cited_by_count":13,"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":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","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":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2405.20250","title":"Entropy annealing for policy mirror descent in continuous time and space","created":"2024-05-30","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":"2211.13668","title":"Zeroth-Order Alternating Gradient Descent Ascent Algorithms for a Class of Nonconvex-Nonconcave Minimax Problems","created":"2022-11-24","cited_by_count":11,"area":null},{"id":"2310.01362","title":"Robot Fleet Learning via Policy Merging","created":"2023-10-02","cited_by_count":11,"area":null},{"id":"2402.17722","title":"Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence","created":"2024-02-27","cited_by_count":11,"area":null},{"id":"2204.05466","title":"Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization","created":"2022-04-12","cited_by_count":10,"area":null},{"id":"2206.02953","title":"Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization","created":"2022-06-07","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":"2212.07534","title":"Decentralized Nonconvex Optimization with Guaranteed Privacy and Accuracy","created":"2022-12-14","cited_by_count":10,"area":null},{"id":"2302.13144","title":"Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient","created":"2023-02-25","cited_by_count":10,"area":null},{"id":"2312.00561","title":"A safe exploration approach to constrained Markov decision processes","created":"2023-12-01","cited_by_count":10,"area":null},{"id":"2301.12624","title":"Learning the Kalman Filter with Fine-Grained Sample Complexity","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2310.02671","title":"Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods","created":"2023-10-04","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":"2210.12812","title":"Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence","created":"2022-10-23","cited_by_count":8,"area":null},{"id":"2310.15418","title":"Fractal Landscapes in Policy Optimization","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2109.13391","title":"Curvature-Aware Derivative-Free Optimization","created":"2021-09-27","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":"2203.11758","title":"Linear convergence of a policy gradient method for some finite horizon continuous time control problems","created":"2022-03-22","cited_by_count":7,"area":null},{"id":"2210.11577","title":"Global Convergence of Direct Policy Search for State-Feedback $\\mathcal{H}_\\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2304.10951","title":"A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2307.11044","title":"On the Convergence of Bounded Agents","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2405.00871","title":"Learning to Boost the Performance of Stable Nonlinear Systems","created":"2024-05-01","cited_by_count":7,"area":null},{"id":"2508.16817","title":"Predictability Enables Parallelization of Nonlinear State Space Models","created":"2025-08-22","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":"2106.07814","title":"Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity","created":"2021-06-15","cited_by_count":6,"area":null},{"id":"2202.13046","title":"Distributed Multi-Agent Reinforcement Learning Based on Graph-Induced Local Value Functions","created":"2022-02-26","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":"2311.18736","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","created":"2023-11-30","cited_by_count":6,"area":null},{"id":"2502.06545","title":"Universal Sequence Preconditioning","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2101.02137","title":"Smoothed functional-based gradient algorithms for off-policy reinforcement learning: A non-asymptotic viewpoint","created":"2021-01-06","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":"2111.00185","title":"Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2111.15537","title":"Model-Free $\\mu$ Synthesis via Adversarial Reinforcement Learning","created":"2021-11-30","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":"2303.08431","title":"Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators","created":"2023-03-15","cited_by_count":5,"area":null},{"id":"2306.02422","title":"A Generalized Alternating Method for Bilevel Learning under the Polyak-{\\L}ojasiewicz Condition","created":"2023-06-04","cited_by_count":5,"area":null},{"id":"2306.10486","title":"On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization","created":"2023-06-18","cited_by_count":5,"area":null},{"id":"2309.06588","title":"Convergence of Gradient-based MAML in LQR","created":"2023-09-12","cited_by_count":5,"area":null},{"id":"2402.02857","title":"Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2103.15010","title":"On the Stability of Nonlinear Receding Horizon Control: A Geometric Perspective","created":"2021-03-27","cited_by_count":4,"area":null},{"id":"2107.12416","title":"Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent","created":"2021-07-26","cited_by_count":4,"area":null},{"id":"2110.13799","title":"Neural PPO-Clip Attains Global Optimality: A Hinge Loss Perspective","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2111.15228","title":"Global Convergence Using Policy Gradient Methods for Model-free Markovian Jump Linear Quadratic Control","created":"2021-11-30","cited_by_count":4,"area":null},{"id":"2202.06637","title":"Continuous-time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations","created":"2022-02-14","cited_by_count":4,"area":null},{"id":"2309.04272","title":"Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2309.04831","title":"Global Convergence of Receding-Horizon Policy Search in Learning Estimator Designs","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2310.11897","title":"Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning","created":"2023-10-18","cited_by_count":4,"area":null},{"id":"2310.19022","title":"Optimization Landscape of Policy Gradient Methods for Discrete-time Static Output Feedback","created":"2023-10-29","cited_by_count":4,"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":"2203.13854","title":"Quasi-Newton Iteration in Deterministic Policy Gradient","created":"2022-03-25","cited_by_count":3,"area":null},{"id":"2207.09090","title":"Actor-Critic based Improper Reinforcement Learning","created":"2022-07-19","cited_by_count":3,"area":null},{"id":"2303.12981","title":"Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2405.02041","title":"Stabilizing Backpropagation Through Time to Learn Complex Physics","created":"2024-05-03","cited_by_count":3,"area":null},{"id":"2505.01348","title":"Learning Stabilizing Policies via an Unstable Subspace Representation","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2202.07808","title":"Policy Learning and Evaluation with Randomized Quasi-Monte Carlo","created":"2022-02-16","cited_by_count":2,"area":null}],"next_cursor":"100"}