v1v2 (latest)

Going Beyond Linear RL: Sample Efficient Neural Function Approximation

14 July 2021

Kaixuan Huang

Papers citing "Going Beyond Linear RL: Sample Efficient Neural Function Approximation"

50 / 57 papers shown

Title
Optimal Gradient-based Algorithms for Non-concave Bandit Optimization Baihe Huang Kaixuan Huang Sham Kakade Jason D. Lee Qi Lei Runzhe Wang Jiaqi Yang 402 17 0 09 Jul 2021
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity Dhruv Malik Aldo Pacchiano Vishwak Srinivasan Yuanzhi Li 53 6 0 15 Jun 2021
Label Noise SGD Provably Prefers Flat Global Minimizers Alexandru Damian Tengyu Ma Jason D. Lee NoLa 109 120 0 11 Jun 2021
An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap Yuanhao Wang Ruosong Wang Sham Kakade OffRL 171 43 0 23 Mar 2021
Bilinear Classes: A Structural Framework for Provable Generalization in RL S. Du Sham Kakade Jason D. Lee Shachar Lovett G. Mahajan Wen Sun Ruosong Wang OffRL 171 191 0 19 Mar 2021
Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature Kefan Dong Jiaqi Yang Tengyu Ma 74 33 0 08 Feb 2021
Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms Chi Jin Qinghua Liu Sobhan Miryoosefi OffRL 91 219 0 01 Feb 2021
Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints Chi Jin Zhuoran Yang Zhaoran Wang OffRL 251 168 0 06 Jan 2021
Beyond Lazy Training for Over-parameterized Tensor Decomposition Xiang Wang Chenwei Wu Jason D. Lee Tengyu Ma Rong Ge 60 14 0 22 Oct 2020
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions Gellert Weisz Philip Amortila Csaba Szepesvári OffRL 158 80 0 03 Oct 2020
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy E. Moroshko Suriya Gunasekar Blake E. Woodworth Jason D. Lee Nathan Srebro Daniel Soudry 68 86 0 13 Jul 2020
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks Cong Fang Jason D. Lee Pengkun Yang Tong Zhang OOD FedML 133 58 0 03 Jul 2020
Towards Understanding Hierarchical Learning: Benefits of Neural Representations Minshuo Chen Yu Bai Jason D. Lee T. Zhao Huan Wang Caiming Xiong R. Socher SSL 68 49 0 24 Jun 2020
Shape Matters: Understanding the Implicit Bias of the Noise Covariance Jeff Z. HaoChen Colin Wei Jason D. Lee Tengyu Ma 168 95 0 15 Jun 2020
Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension Ruosong Wang Ruslan Salakhutdinov Lin F. Yang 65 55 0 21 May 2020
Learning Near Optimal Policies with Low Inherent Bellman Error Andrea Zanette A. Lazaric Mykel Kochenderfer Emma Brunskill OffRL 73 222 0 29 Feb 2020
Few-Shot Learning via Learning the Representation, Provably S. Du Wei Hu Sham Kakade Jason D. Lee Qi Lei SSL 46 261 0 21 Feb 2020
Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity S. Du Jason D. Lee G. Mahajan Ruosong Wang 43 37 0 17 Feb 2020
Dota 2 with Large Scale Deep Reinforcement Learning OpenAI OpenAI : Christopher Berner Greg Brockman Brooke Chan ... Szymon Sidor Ilya Sutskever Jie Tang Filip Wolski Susan Zhang GNN VLM CLL AI4CE LRM 169 1,835 0 13 Dec 2019
Optimism in Reinforcement Learning with Generalized Linear Function Approximation Yining Wang Ruosong Wang S. Du A. Krishnamurthy 182 137 0 09 Dec 2019
Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? S. Du Sham Kakade Ruosong Wang Lin F. Yang 186 193 0 07 Oct 2019
Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks Yu Bai Jason D. Lee 52 116 0 03 Oct 2019
$$\sqrt{n}$-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank$ $\sqrt{n}$ -Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank Kefan Dong Jian-wei Peng Yining Wang Yuanshuo Zhou OffRL 56 36 0 05 Sep 2019
Neural Policy Gradient Methods: Global Optimality and Rates of Convergence Lingxiao Wang Qi Cai Zhuoran Yang Zhaoran Wang 89 242 0 29 Aug 2019
Exploration-Enhanced POLITEX Yasin Abbasi-Yadkori N. Lazić Csaba Szepesvári Gellert Weisz 55 23 0 27 Aug 2019
Robust and Resource Efficient Identification of Two Hidden Layer Neural Networks M. Fornasier T. Klock Michael Rauchensteiner 65 18 0 30 Jun 2019
Neural Proximal/Trust Region Policy Optimization Attains Globally Optimal Policy Boyi Liu Qi Cai Zhuoran Yang Zhaoran Wang 73 111 0 25 Jun 2019
Worst-Case Regret Bounds for Exploration via Randomized Value Functions Daniel Russo OffRL 48 86 0 07 Jun 2019
Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound Lin F. Yang Mengdi Wang OffRL GP 64 287 0 24 May 2019
What Can ResNet Learn Efficiently, Going Beyond Kernels? Zeyuan Allen-Zhu Yuanzhi Li 396 183 0 24 May 2019
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models Mor Shpigel Nacson Suriya Gunasekar Jason D. Lee Nathan Srebro Daniel Soudry 78 94 0 17 May 2019
Linearized two-layers neural networks in high dimension Behrooz Ghorbani Song Mei Theodor Misiakiewicz Andrea Montanari MLT 60 243 0 27 Apr 2019
On the Power and Limitations of Random Features for Understanding Neural Networks Gilad Yehudai Ohad Shamir MLT 85 182 0 01 Apr 2019
Provably efficient RL with Rich Observations via Latent State Decoding S. Du A. Krishnamurthy Nan Jiang Alekh Agarwal Miroslav Dudík John Langford OffRL 74 230 0 25 Jan 2019
Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds Andrea Zanette Emma Brunskill OffRL 106 279 0 01 Jan 2019
Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks Difan Zou Yuan Cao Dongruo Zhou Quanquan Gu ODL 190 448 0 21 Nov 2018
A Convergence Theory for Deep Learning via Over-Parameterization Zeyuan Allen-Zhu Yuanzhi Li Zhao Song AI4CE ODL 264 1,466 0 09 Nov 2018
Gradient Descent Finds Global Minima of Deep Neural Networks S. Du Jason D. Lee Haochuan Li Liwei Wang Masayoshi Tomizuka ODL 211 1,135 0 09 Nov 2018
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel Colin Wei Jason D. Lee Qiang Liu Tengyu Ma 214 245 0 12 Oct 2018
Is Q-learning Provably Efficient? Chi Jin Zeyuan Allen-Zhu Sébastien Bubeck Michael I. Jordan OffRL 75 812 0 10 Jul 2018
Neural Tangent Kernel: Convergence and Generalization in Neural Networks Arthur Jacot Franck Gabriel Clément Hongler 271 3,213 0 20 Jun 2018
Practical Contextual Bandits with Regression Oracles Dylan J. Foster Alekh Agarwal Miroslav Dudík Haipeng Luo Robert Schapire 393 127 0 03 Mar 2018
On Oracle-Efficient PAC RL with Rich Observations Christoph Dann Nan Jiang A. Krishnamurthy Alekh Agarwal John Langford Robert Schapire 49 98 0 01 Mar 2018
Learning One-hidden-layer Neural Networks with Landscape Design Rong Ge Jason D. Lee Tengyu Ma MLT 206 262 0 01 Nov 2017
Deep Reinforcement Learning that Matters Peter Henderson Riashat Islam Philip Bachman Joelle Pineau Doina Precup David Meger OffRL 121 1,961 0 19 Sep 2017
Recovery Guarantees for One-hidden-layer Neural Networks Kai Zhong Zhao Song Prateek Jain Peter L. Bartlett Inderjit S. Dhillon MLT 175 337 0 10 Jun 2017
Minimax Regret Bounds for Reinforcement Learning M. G. Azar Ian Osband Rémi Munos 90 778 0 16 Mar 2017
Active Learning for Cost-Sensitive Classification A. Krishnamurthy Alekh Agarwal Tzu-Kuo Huang Hal Daumé John Langford 217 79 0 03 Mar 2017
DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker Matej Moravcík Martin Schmid Neil Burch Viliam Lisý Dustin Morrill Nolan Bard Trevor Davis Kevin Waugh Michael Bradley Johanson Michael Bowling BDL 188 911 0 06 Jan 2017
Contextual Decision Processes with Low Bellman Rank are PAC-Learnable Nan Jiang A. Krishnamurthy Alekh Agarwal John Langford Robert Schapire 152 420 0 29 Oct 2016