Naive Exploration is Optimal for Online LQR

27 January 2020

Max Simchowitz

Papers citing "Naive Exploration is Optimal for Online LQR"

46 / 46 papers shown

Title
Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation Runze Zhao Yue Yu Adams Yiyue Zhu Chen Yang Dongruo Zhou 12 0 0 20 May 2025
Predictive Control and Regret Analysis of Non-Stationary MDP with Look-ahead Information Ziyi Zhang Yorie Nakahira Guannan Qu 36 1 0 13 Sep 2024
NeoRL: Efficient Exploration for Nonepisodic RL Bhavya Sukhija Lenart Treven Florian Dorfler Stelian Coros Andreas Krause OffRL 41 0 0 03 Jun 2024
Quantum Non-Identical Mean Estimation: Efficient Algorithms and Fundamental Limits Jiachen Hu Tongyang Li Xinzhao Wang Yecheng Xue Chenyi Zhang Han Zhong 31 0 0 21 May 2024
On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR Jaeuk Shin Giho Kim Howon Lee Joonho Han Insoon Yang OffRL 41 1 0 09 Dec 2023
Optimal Exploration for Model-Based RL in Nonlinear Systems Andrew Wagenmaker Guanya Shi Kevin G. Jamieson 41 14 0 15 Jun 2023
Optimal Rates for Bandit Nonstochastic Control Y. Jennifer Sun Stephen Newman Elad Hazan 37 7 0 24 May 2023
Suboptimality analysis of receding horizon quadratic control with unknown linear systems and its applications in learning-based control Shengli Shi Anastasios Tsiamis B. de Schutter 23 2 0 19 Jan 2023
PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models Deividas Eringis J. Leth Zheng-Hua Tan Rafal Wisniewski Mihaly Petreczky 32 1 0 30 Dec 2022
Towards a Theoretical Foundation of Policy Optimization for Learning Control Policies Bin Hu Kaipeng Zhang Na Li M. Mesbahi Maryam Fazel Tamer Bacsar 89 27 0 10 Oct 2022
Statistical Learning Theory for Control: A Finite Sample Perspective Anastasios Tsiamis Ingvar M. Ziemann Nikolai Matni George J. Pappas 28 73 0 12 Sep 2022
Meta-Learning Online Control for Linear Dynamical Systems Deepan Muthirayan D. Kalathil Pramod P. Khargonekar 35 6 0 18 Aug 2022
Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning Lukasz Szpruch Tanut Treetanthiploet Yufei Zhang 36 8 0 08 Aug 2022
$Thompson Sampling Achieves $\tilde O(\sqrt{T})$ Regret in Linear Quadratic Control$ Thompson Sampling Achieves $\tilde O(\sqrt{T})$ Regret in Linear Quadratic Control Taylan Kargin Sahin Lale Kamyar Azizzadenesheli Anima Anandkumar B. Hassibi 23 11 0 17 Jun 2022
Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity Alekh Agarwal Tong Zhang 52 22 0 15 Jun 2022
How are policy gradient methods affected by the limits of control? Ingvar M. Ziemann Anastasios Tsiamis H. Sandberg Nikolai Matni 25 14 0 14 Jun 2022
Learning to Control under Time-Varying Environment Yuzhen Han Rubén Solozabal Jing Dong Xingyu Zhou Martin Takáč B. Gu 18 2 0 06 Jun 2022
Rate-Optimal Online Convex Optimization in Adaptive Linear Control Asaf B. Cassel Alon Cohen Google Research 34 9 0 03 Jun 2022
Learning to Control Linear Systems can be Hard Anastasios Tsiamis Ingvar M. Ziemann M. Morari Nikolai Matni George J. Pappas 24 14 0 27 May 2022
Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics Asaf B. Cassel Alon Cohen Google Research 23 5 0 02 Mar 2022
Learning Mixtures of Linear Dynamical Systems Yanxi Chen H. Vincent Poor 25 17 0 26 Jan 2022
Exponential Family Model-Based Reinforcement Learning via Score Matching Gen Li Junbo Li Anmol Kabra Nathan Srebro Zhaoran Wang Zhuoran Yang 37 4 0 28 Dec 2021
Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models Lukasz Szpruch Tanut Treetanthiploet Yufei Zhang 21 24 0 19 Dec 2021
Learning over All Stabilizing Nonlinear Controllers for a Partially-Observed Linear System Ruigang Wang Nicholas H. Barbara Max Revay I. Manchester 22 16 0 08 Dec 2021
A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning Tongzheng Ren Tianjun Zhang Csaba Szepesvári Bo Dai 27 19 0 22 Nov 2021
Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees Yingying Li Subhro Das J. Shamma Na Li 22 25 0 31 Oct 2021
Provable Regret Bounds for Deep Online Learning and Control Xinyi Chen Edgar Minasyan Jason D. Lee Elad Hazan 41 6 0 15 Oct 2021
Stabilizing Dynamical Systems via Policy Gradient Methods Juan C. Perdomo Jack Umenberger Max Simchowitz 40 44 0 13 Oct 2021
A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems Mukul Gagrani Sagar Sudhakara Aditya Mahajan Rahul Jain Yi Ouyang 36 6 0 19 Aug 2021
Koopman Spectrum Nonlinear Regulators and Efficient Online Learning Motoya Ohnishi Isao Ishikawa Kendall Lowrey Masahiro Ikeda Sham Kakade Yoshinobu Kawahara 23 5 0 30 Jun 2021
Meta-Adaptive Nonlinear Control: Theory and Algorithms Guanya Shi Kamyar Azizzadenesheli Michael O'Connell Soon-Jo Chung Yisong Yue 34 41 0 11 Jun 2021
Regret Analysis of Distributed Online LQR Control for Unknown LTI Systems Ting-Jui Chang Shahin Shahrampour 32 8 0 15 May 2021
Online Learning for Unknown Partially Observable MDPs Mehdi Jafarnia-Jahromi Rahul Jain A. Nayyar 34 20 0 25 Feb 2021
$Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt{T}$ Regret$ Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with $\sqrt{T}$ Regret Asaf B. Cassel Tomer Koren OffRL 36 17 0 25 Feb 2021
Task-Optimal Exploration in Linear Dynamical Systems Andrew Wagenmaker Max Simchowitz Kevin G. Jamieson 29 18 0 10 Feb 2021
Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints Chi Jin Zhuoran Yang Zhaoran Wang OffRL 122 167 0 06 Jan 2021
Regret Bounds for Adaptive Nonlinear Control Nicholas M. Boffi Stephen Tu Jean-Jacques E. Slotine 43 47 0 26 Nov 2020
Thompson sampling for linear quadratic mean-field teams Mukul Gagrani Sagar Sudhakara Aditya Mahajan A. Nayyar Ouyang Yi 26 4 0 09 Nov 2020
SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory Paria Rashidinejad Jiantao Jiao Stuart J. Russell 26 11 0 12 Oct 2020
Bandit Linear Control Asaf B. Cassel Tomer Koren 8 17 0 01 Jul 2020
Information Theoretic Regret Bounds for Online Nonlinear Control Sham Kakade A. Krishnamurthy Kendall Lowrey Motoya Ohnishi Wen Sun 38 117 0 22 Jun 2020
Learning Stabilizing Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory Lenart Treven Sebastian Curi Mojmír Mutný Andreas Krause 13 4 0 19 Jun 2020
Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems Sahin Lale Kamyar Azizzadenesheli B. Hassibi Anima Anandkumar 40 92 0 25 Mar 2020
Logarithmic Regret for Adversarial Online Control Dylan J. Foster Max Simchowitz 17 72 0 29 Feb 2020
Improper Learning for Non-Stochastic Control Max Simchowitz Karan Singh Elad Hazan 24 153 0 25 Jan 2020
Spectral Filtering for General Linear Dynamical Systems Elad Hazan Holden Lee Karan Singh Cyril Zhang Yi Zhang 47 97 0 12 Feb 2018