{"list":"other","total":79,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"1709.10087","title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","created":"2017-09-28","cited_by_count":715},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1703.00887","title":"How to Escape Saddle Points Efficiently","created":"2017-03-02","cited_by_count":285},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"1801.05039","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","created":"2018-01-15","cited_by_count":250},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"id":"1710.01688","title":"On the Sample Complexity of the Linear Quadratic Regulator","created":"2017-10-04","cited_by_count":159},{"id":"1806.09460","title":"A Tour of Reinforcement Learning: The View from Continuous Control","created":"2018-06-25","cited_by_count":151},{"id":"2001.09576","title":"Naive Exploration is Optimal for Online LQR","created":"2020-01-27","cited_by_count":116},{"id":"1902.08721","title":"Online Control with Adversarial Disturbances","created":"2019-02-23","cited_by_count":92},{"id":"2001.09254","title":"Improper Learning for Non-Stochastic Control","created":"2020-01-25","cited_by_count":83},{"id":"1509.03025","title":"Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees","created":"2015-09-10","cited_by_count":70},{"id":"1812.08305","title":"Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems","created":"2018-12-20","cited_by_count":67},{"id":"1711.10467","title":"Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution","created":"2017-11-28","cited_by_count":63},{"id":"2209.05423","title":"Statistical Learning Theory for Control: A Finite Sample Perspective","created":"2022-09-12","cited_by_count":53},{"id":"2011.10300","title":"Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon","created":"2020-11-20","cited_by_count":50},{"id":"1910.09496","title":"Policy Optimization for $\\mathcal{H}_2$ Linear Control with $\\mathcal{H}_\\infty$ Robustness Guarantee: Implicit Regularization and Global Convergence","created":"2019-10-21","cited_by_count":46},{"id":"1912.11899","title":"Convergence and sample complexity of gradient methods for the model-free linear quadratic regulator problem","created":"2019-12-26","cited_by_count":46},{"id":"2007.06650","title":"Black-Box Control for Linear Dynamical Systems","created":"2020-07-13","cited_by_count":43},{"id":"1906.00729","title":"Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games","created":"2019-05-31","cited_by_count":42},{"id":"1812.03565","title":"The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint","created":"2018-12-09","cited_by_count":40},{"id":"1907.08921","title":"LQR through the Lens of First Order Methods: Discrete-time Case","created":"2019-07-21","cited_by_count":40},{"id":"1605.07051","title":"Convergence Analysis for Rectangular Matrix Completion Using Burer-Monteiro Factorization and Gradient Descent","created":"2016-05-23","cited_by_count":39},{"id":"1912.09135","title":"Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach","created":"2019-12-19","cited_by_count":38},{"id":"2102.09161","title":"On the Sample Complexity of Stability Constrained Imitation Learning","created":"2021-02-18","cited_by_count":38},{"id":"1602.02915","title":"Calculus of the exponent of Kurdyka-{\\L}ojasiewicz inequality and its applications to linear convergence of first-order methods","created":"2016-02-09","cited_by_count":35},{"id":"2012.09293","title":"Imitation Learning with Stability and Safety Guarantees","created":"2020-12-16","cited_by_count":34},{"id":"1906.07355","title":"Escaping from saddle points on Riemannian manifolds","created":"2019-06-18","cited_by_count":33},{"id":"1910.04295","title":"Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods","created":"2019-10-09","cited_by_count":28},{"id":"2102.04393","title":"Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Control","created":"2021-02-08","cited_by_count":28},{"id":"2004.09875","title":"Optimizing Static Linear Feedback: Gradient Method","created":"2020-04-21","cited_by_count":27},{"id":"2110.06418","title":"Stabilizing Dynamical Systems via Policy Gradient Methods","created":"2021-10-13","cited_by_count":25},{"id":"1804.11003","title":"Gradient Sampling Methods for Nonsmooth Optimization","created":"2018-04-29","cited_by_count":23},{"id":"1905.12842","title":"Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator","created":"2019-05-30","cited_by_count":23},{"id":"1912.08774","title":"Learning the Globally Optimal Distributed LQ Regulator","created":"2019-12-18","cited_by_count":20},{"id":"2008.06845","title":"Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time","created":"2020-08-16","cited_by_count":20},{"id":"1910.07498","title":"Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games","created":"2019-10-16","cited_by_count":19},{"id":"1906.11392","title":"From self-tuning regulators to reinforcement learning and back again","created":"2019-06-27","cited_by_count":17},{"id":"1907.03712","title":"Policy-Gradient Algorithms Have No Guarantees of Convergence in Linear Quadratic Games","created":"2019-07-08","cited_by_count":17},{"id":"1910.13399","title":"Robust Model-free Reinforcement Learning with Multi-objective Bayesian Optimization","created":"2019-10-29","cited_by_count":16},{"id":"1911.04672","title":"Global Convergence of Policy Gradient for Sequential Zero-Sum Linear Quadratic Dynamic Games","created":"2019-11-12","cited_by_count":16},{"id":"2104.04901","title":"Global Convergence of Policy Gradient Primal-dual Methods for Risk-constrained LQRs","created":"2021-04-11","cited_by_count":16},{"id":"2005.09528","title":"Robust Policy Iteration for Continuous-time Linear Quadratic Regulation","created":"2020-05-19","cited_by_count":15},{"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},{"id":"2006.09178","title":"Policy Gradient-based Algorithms for Continuous-time Linear Quadratic Control","created":"2020-06-12","cited_by_count":13},{"id":"2201.09598","title":"On the Optimization Landscape of Dynamic Output Feedback Linear Quadratic Control","created":"2022-01-24","cited_by_count":11},{"id":"1903.01997","title":"Implicit Regularization in Over-parameterized Neural Networks","created":"2019-03-05","cited_by_count":10},{"id":"2103.12945","title":"On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI Conditions","created":"2021-03-24","cited_by_count":10},{"id":"2206.06863","title":"How are policy gradient methods affected by the limits of control?","created":"2022-06-14","cited_by_count":10},{"id":"2001.07572","title":"Fitting a Linear Control Policy to Demonstrations with a Kalman Constraint","created":"2020-01-21","cited_by_count":9},{"id":"2109.13132","title":"Optimization Landscape of Gradient Descent for Discrete-time Static Output Feedback","created":"2021-09-27","cited_by_count":9},{"id":"2011.10931","title":"Primal-dual Learning for the Model-free Risk-constrained Linear Quadratic Regulator","created":"2020-11-22","cited_by_count":8},{"id":"2202.11659","title":"Globally Convergent Policy Search over Dynamic Filters for Output Estimation","created":"2022-02-23","cited_by_count":8},{"id":"1904.02737","title":"On Topological and Metrical Properties of Stabilizing Feedback Gains: the MIMO Case","created":"2019-04-04","cited_by_count":7},{"id":"2002.04090","title":"Convergence Guarantees of Policy Optimization Methods for Markovian Jump Linear Systems","created":"2020-02-10","cited_by_count":7},{"id":"2008.11592","title":"Robust Reinforcement Learning: A Case Study in Linear Quadratic Regulation","created":"2020-08-25","cited_by_count":7},{"id":"2011.09728","title":"Zeroth-Order Feedback Optimization for Cooperative Multi-Agent Systems","created":"2020-11-19","cited_by_count":7},{"id":"2103.15363","title":"Infinite-horizon Risk-constrained Linear Quadratic Regulator with Average Cost","created":"2021-03-29","cited_by_count":7},{"id":"2006.03116","title":"Policy Learning of MDPs with Mixed Continuous/Discrete Variables: A Case Study on Model-Free Control of Markovian Jump Systems","created":"2020-06-04","cited_by_count":6},{"id":"2007.03861","title":"On the Analysis of Model-free Methods for the Linear Quadratic Regulator","created":"2020-07-08","cited_by_count":6},{"id":"2203.11177","title":"Connectivity of the Feasible and Sublevel Sets of Dynamic Output Feedback Control with Robustness Constraints","created":"2022-03-21","cited_by_count":6},{"id":"1810.09337","title":"Recovering Robustness in Model-Free Reinforcement learning","created":"2018-10-22","cited_by_count":5},{"id":"2111.15537","title":"Model-Free $\\mu$ Synthesis via Adversarial Reinforcement Learning","created":"2021-11-30","cited_by_count":5},{"id":"2201.11157","title":"Policy Optimization over Submanifolds for Linearly Constrained Feedback Synthesis","created":"2022-01-26","cited_by_count":5},{"id":"2204.00912","title":"Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control","created":"2022-04-02","cited_by_count":5},{"id":"2009.02146","title":"Policy Optimization for Linear-Quadratic Zero-Sum Mean-Field Type Games","created":"2020-09-02","cited_by_count":4},{"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},{"id":"2002.05023","title":"Global Convergence of Policy Gradient Algorithms for Indefinite Least Squares Stationary Optimal Control","created":"2020-02-10","cited_by_count":3},{"id":"1903.08634","title":"Aggressive Local Search for Constrained Optimal Control Problems with Many Local Minima","created":"2019-03-20","cited_by_count":1}],"next_cursor":null}