{"list":"other","total":62,"rows":[{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"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":"1801.05039","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","created":"2018-01-15","cited_by_count":250},{"id":"1710.01688","title":"On the Sample Complexity of the Linear Quadratic Regulator","created":"2017-10-04","cited_by_count":159},{"id":"1802.08334","title":"Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification","created":"2018-02-22","cited_by_count":158},{"id":"2001.09576","title":"Naive Exploration is Optimal for Online LQR","created":"2020-01-27","cited_by_count":116},{"id":"1507.03566","title":"Low-rank Solutions of Linear Matrix Equations via Procrustes Flow","created":"2015-07-13","cited_by_count":97},{"id":"1812.01251","title":"Near optimal finite time identification of arbitrary linear dynamical systems","created":"2018-12-04","cited_by_count":89},{"id":"1805.09388","title":"Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator","created":"2018-05-23","cited_by_count":86},{"id":"2001.09254","title":"Improper Learning for Non-Stochastic Control","created":"2020-01-25","cited_by_count":83},{"id":"2006.10277","title":"Active Learning for Nonlinear System Identification with Guarantees","created":"2020-06-18","cited_by_count":80},{"id":"1609.05191","title":"Gradient Descent Learns Linear Dynamical Systems","created":"2016-09-16","cited_by_count":79},{"id":"1902.06223","title":"Learning Linear-Quadratic Regulators Efficiently with only $\\sqrt{T}$ Regret","created":"2019-02-17","cited_by_count":70},{"id":"1903.09122","title":"Finite Sample Analysis of Stochastic System Identification","created":"2019-03-21","cited_by_count":67},{"id":"1710.01852","title":"Finite Time Identification in Unstable Linear Systems","created":"2017-10-05","cited_by_count":66},{"id":"1902.00768","title":"Learning Linear Dynamical Systems with Semi-Parametric Least Squares","created":"2019-02-02","cited_by_count":58},{"id":"2006.08916","title":"Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms","created":"2020-06-16","cited_by_count":56},{"id":"1401.0304","title":"Learning without Concentration","created":"2014-01-01","cited_by_count":50},{"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":"2003.11227","title":"Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems","created":"2020-03-25","cited_by_count":46},{"id":"2004.14681","title":"Learning nonlinear dynamical systems from a single trajectory","created":"2020-04-30","cited_by_count":46},{"id":"2110.00675","title":"Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overview","created":"2021-10-01","cited_by_count":45},{"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":"2002.08538","title":"Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems","created":"2020-02-20","cited_by_count":39},{"id":"2009.00739","title":"Non-asymptotic Identification of Linear Dynamical Systems Using Multiple Trajectories","created":"2020-09-01","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":"2002.08095","title":"Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently","created":"2020-02-19","cited_by_count":35},{"id":"1912.10754","title":"Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices","created":"2019-12-23","cited_by_count":34},{"id":"1809.10121","title":"Safely Learning to Control the Constrained Linear Quadratic Regulator","created":"2018-09-26","cited_by_count":33},{"id":"2002.00495","title":"Active Learning for Identification of Linear Dynamical Systems","created":"2020-02-02","cited_by_count":33},{"id":"2206.08269","title":"Learning with little mixing","created":"2022-06-16","cited_by_count":33},{"id":"2003.07937","title":"Finite-time Identification of Stable Linear Systems: Optimality of the Least-Squares Estimator","created":"2020-03-17","cited_by_count":26},{"id":"2202.08311","title":"Single Trajectory Nonparametric Learning of Nonlinear Dynamics","created":"2022-02-16","cited_by_count":26},{"id":"2110.06418","title":"Stabilizing Dynamical Systems via Policy Gradient Methods","created":"2021-10-13","cited_by_count":25},{"id":"2203.17193","title":"Learning from many trajectories","created":"2022-03-31","cited_by_count":24},{"id":"2002.05141","title":"Online Learning of the Kalman Filter with Logarithmic Regret","created":"2020-02-12","cited_by_count":21},{"id":"2205.14812","title":"TaSIL: Taylor Series Imitation Learning","created":"2022-05-30","cited_by_count":21},{"id":"1903.10343","title":"Sample Complexity Lower Bounds for Linear System Identification","created":"2019-03-25","cited_by_count":20},{"id":"1904.09396","title":"Learning Sparse Dynamical Systems from a Single Sample Trajectory","created":"2019-04-20","cited_by_count":20},{"id":"2104.01120","title":"Linear Systems can be Hard to Learn","created":"2021-04-02","cited_by_count":20},{"id":"1906.11395","title":"A Tutorial on Concentration Bounds for System Identification","created":"2019-06-27","cited_by_count":19},{"id":"1811.04258","title":"Input Perturbations for Adaptive Control and Learning","created":"2018-11-10","cited_by_count":18},{"id":"2002.02064","title":"No-Regret Prediction in Marginally Stable Systems","created":"2020-02-06","cited_by_count":18},{"id":"2007.06482","title":"Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation","created":"2020-07-13","cited_by_count":18},{"id":"2105.11558","title":"Near-optimal Offline and Streaming Algorithms for Learning Non-Linear Dynamical Systems","created":"2021-05-24","cited_by_count":17},{"id":"1707.04791","title":"Non-Asymptotic Analysis of Robust Control from Coarse-Grained Identification","created":"2017-07-15","cited_by_count":16},{"id":"1809.05870","title":"On-Line Learning of Linear Dynamical Systems: Exponential Forgetting in Kalman Filters","created":"2018-09-16","cited_by_count":16},{"id":"2102.05214","title":"Task-Optimal Exploration in Linear Dynamical Systems","created":"2021-02-10","cited_by_count":15},{"id":"2111.07018","title":"Identification and Adaptive Control of Markov Jump Systems: Sample Complexity and Regret Bounds","created":"2021-11-13","cited_by_count":14},{"id":"1410.3192","title":"Learning without Concentration for General Loss Functions","created":"2014-10-13","cited_by_count":13},{"id":"2109.14429","title":"Minimal Expected Regret in Linear Quadratic Control","created":"2021-09-29","cited_by_count":13},{"id":"2011.10006","title":"Improved rates for prediction and identification of partially observed linear dynamical systems","created":"2020-11-19","cited_by_count":12},{"id":"2010.05899","title":"SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory","created":"2020-10-12","cited_by_count":11},{"id":"2201.01680","title":"Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems","created":"2022-01-05","cited_by_count":11},{"id":"2205.14035","title":"Learning to Control Linear Systems can be Hard","created":"2022-05-27","cited_by_count":11},{"id":"1709.04047","title":"Learning-based Control of Unknown Linear Systems with Thompson Sampling","created":"2017-09-12","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":"1909.02192","title":"Non-asymptotic Closed-Loop System Identification using Autoregressive Processes and Hankel Model Reduction","created":"2019-09-05","cited_by_count":9},{"id":"2010.04015","title":"Learning Partially Observed Linear Dynamical Systems from Logarithmic Number of Samples","created":"2020-10-08","cited_by_count":9},{"id":"2202.01625","title":"Efficient learning of hidden state LTI state space models of unknown order","created":"2022-02-03","cited_by_count":7},{"id":"1803.09186","title":"Finite-Data Performance Guarantees for the Output-Feedback Control of an Unknown System","created":"2018-03-25","cited_by_count":4},{"id":"2105.10280","title":"Near-Optimal Design of Safe Output Feedback Controllers from Noisy Data","created":"2021-05-21","cited_by_count":1}],"next_cursor":null}