v1v2v3v4v5 (latest)

A general sample complexity analysis of vanilla policy gradient

International Conference on Artificial Intelligence and Statistics (AISTATS), 2021

23 July 2021

Papers citing "A general sample complexity analysis of vanilla policy gradient"

50 / 51 papers shown

Title
On the Sample Complexity of Differentially Private Policy Optimization Yi He Xingyu Zhou 77 0 0 24 Oct 2025
Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential Yuping Zheng Andrew G. Lamperski 144 0 0 03 Oct 2025
Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning Alexander Tyurin Andrei Spiridonov Varvara Rudenko OffRL 100 0 0 29 Sep 2025
On the Convergence of Policy Mirror Descent with Temporal Difference Evaluation Jiacai Liu Wenye Li Ke Wei 84 0 0 23 Sep 2025
GPG-HT: Generalized Policy Gradient with History-Aware Decision Transformer for Probabilistic Path Planning Xing Wei Yuqi Ouyang 28 1 0 24 Aug 2025
Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design Xingyu Su Xiner Li Masatoshi Uehara Sunwoo Kim Yulai Zhao Gabriele Scalia Ehsan Hajiramezanali Tommaso Biancalani D. Zhi Shuiwang Ji 121 5 0 01 Jul 2025
Reusing Trajectories in Policy Gradients Enables Fast Convergence Alessandro Montenegro Federico Mansutti Marco Mussi Matteo Papini Alberto Maria Metelli OnRL 211 0 0 06 Jun 2025
Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach Swetha Ganesh Vaneet Aggarwal 185 2 0 26 May 2025
RobotIQ: Empowering Mobile Robots with Human-Level Planning for Real-World Execution Emmanuel K. Raptis Athanasios Ch. Kapoutsis Elias B. Kosmatopoulos LM&Ro 208 1 0 18 Feb 2025
Convergence of Policy Mirror Descent Beyond Compatible Function Approximation Uri Sherman Tomer Koren Yishay Mansour 295 0 0 16 Feb 2025
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning ratesNeural Information Processing Systems (NeurIPS), 2025 Jincheng Mei Bo Dai Alekh Agarwal Sharan Vaswani Anant Raj Csaba Szepesvári Dale Schuurmans 270 1 0 11 Feb 2025
A learning-based approach to stochastic optimal control under reach-avoid constraintInternational Conference on Hybrid Systems: Computation and Control (HSCC), 2024 Tingting Ni Maryam Kamgarpour 374 1 0 21 Dec 2024
FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHFAdaptive Agents and Multi-Agent Systems (AAMAS), 2024 Flint Xiaofeng Fan Cheston Tan Yew-Soon Ong Roger Wattenhofer Wei Tsang Ooi 388 1 0 20 Dec 2024
Structure Matters: Dynamic Policy Gradient Sara Klein Xiangyuan Zhang Tamer Basar Simon Weissmann Leif Döring 139 1 0 07 Nov 2024
On The Global Convergence Of Online RLHF With Neural Parametrization Mudit Gaur Amrit Singh Bedi Raghu Pasupathy Vaneet Aggarwal 238 1 0 21 Oct 2024
Loss Landscape Characterization of Neural Networks without Over-ParametrizationNeural Information Processing Systems (NeurIPS), 2024 Rustem Islamov Niccolò Ajroldi Antonio Orvieto Aurelien Lucchi 327 9 0 16 Oct 2024
On the Convergence of Single-Timescale Actor-Critic Navdeep Kumar Priyank Agrawal Giorgia Ramponi Kfir Y. Levy Shie Mannor 234 0 0 11 Oct 2024
Towards Fast Rates for Federated and Multi-Task Reinforcement LearningIEEE Conference on Decision and Control (CDC), 2024 Feng Zhu Robert W. Heath Jr. Aritra Mitra 159 2 0 09 Sep 2024
Complexity of Minimizing Projected-Gradient-Dominated Functions with Stochastic First-order Oracles Saeed Masiha Saber Salehkaleybar Niao He Negar Kiyavash Patrick Thiran 157 2 0 03 Aug 2024
Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning Alessandro Montenegro Marco Mussi Matteo Papini Alberto Maria Metelli BDL 153 2 0 15 Jul 2024
Almost sure convergence rates of stochastic gradient methods under gradient domination Simon Weissmann Sara Klein Waïss Azizian Leif Döring 247 6 0 22 May 2024
Policy Gradient with Active Importance Sampling Matteo Papini Giorgio Manganini Alberto Maria Metelli Marcello Restelli OffRL 155 4 0 09 May 2024
Learning Optimal Deterministic Policies with Stochastic Policy GradientsInternational Conference on Machine Learning (ICML), 2024 Alessandro Montenegro Marco Mussi Alberto Maria Metelli Matteo Papini 233 5 0 03 May 2024
Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis Guangchen Lan Dong-Jun Han Abolfazl Hashemi Vaneet Aggarwal Christopher G. Brinton 712 22 0 09 Apr 2024
Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries Swetha Ganesh Jiayu Chen Gugan Thoppe Vaneet Aggarwal FedML 267 4 0 15 Mar 2024
Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis Rui Liu Erfaun Noorani Erfaun Noorani John S. Baras 362 4 0 13 Mar 2024
Towards Provable Log Density Policy Gradient Pulkit Katdare Anant Joshi Katherine Driggs-Campbell 197 0 0 03 Mar 2024
Stochastic Gradient Succeeds for Bandits Jincheng Mei Zixin Zhong Bo Dai Alekh Agarwal Csaba Szepesvári Dale Schuurmans 204 1 0 27 Feb 2024
On the Complexity of Finite-Sum Smooth Optimization under the Polyak-Łojasiewicz Condition Yunyan Bai Yuxing Liu Luo Luo 132 1 0 04 Feb 2024
On the Stochastic (Variance-Reduced) Proximal Gradient Method for Regularized Expected Reward Optimization Ling Liang Haizhao Yang 160 1 0 23 Jan 2024
Global Convergence of Natural Policy Gradient with Hessian-aided Momentum Variance ReductionJournal of Scientific Computing (J. Sci. Comput.), 2024 Jie Feng Ke Wei Jinchi Chen 308 3 0 02 Jan 2024
A safe exploration approach to constrained Markov decision processesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Tingting Ni Maryam Kamgarpour 286 4 0 01 Dec 2023
On the Second-Order Convergence of Biased Policy Gradient AlgorithmsInternational Conference on Machine Learning (ICML), 2023 Siqiao Mu Diego Klabjan 305 4 0 05 Nov 2023
Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision ProcessesInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 Washim Uddin Mondal Vaneet Aggarwal 206 18 0 18 Oct 2023
Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient MethodsInternational Conference on Learning Representations (ICLR), 2023 Sara Klein Simon Weissmann Leif Döring 221 12 0 04 Oct 2023
A Homogenization Approach for Gradient-Dominated Stochastic OptimizationConference on Uncertainty in Artificial Intelligence (UAI), 2023 Jiyuan Tan Chenyu Xue Chuwen Zhang Qi Deng Dongdong Ge Yinyu Ye 127 2 0 21 Aug 2023
Fine-Tuning Language Models with Advantage-Induced Policy Alignment Banghua Zhu Hiteshi Sharma Felipe Vieira Frujeri Shi Dong Chenguang Zhu Michael I. Jordan Jiantao Jiao OSLM 225 47 0 04 Jun 2023
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action SpaceInternational Conference on Machine Learning (ICML), 2023 Anas Barakat Ilyas Fatkhullin Niao He 202 14 0 02 Jun 2023
On the Linear Convergence of Policy Gradient under Hadamard ParameterizationInformation and Inference A Journal of the IMA (JIII), 2023 Jiacai Liu Jinchi Chen Ke Wei 184 3 0 31 May 2023
Decision-Aware Actor-Critic with Function Approximation and Theoretical GuaranteesNeural Information Processing Systems (NeurIPS), 2023 Sharan Vaswani A. Kazemi Reza Babanezhad Nicolas Le Roux OffRL 277 5 0 24 May 2023
Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision ProcessesNeural Information Processing Systems (NeurIPS), 2023 Emmeran Johnson Ciara Pike-Burke Patrick Rebeschini 274 15 0 22 Feb 2023
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate PoliciesInternational Conference on Machine Learning (ICML), 2023 Ilyas Fatkhullin Anas Barakat Anastasia Kireeva Niao He 343 51 0 03 Feb 2023
A Novel Framework for Policy Mirror Descent with General Parameterization and Linear ConvergenceNeural Information Processing Systems (NeurIPS), 2023 Carlo Alfano Rui Yuan Patrick Rebeschini 466 18 0 30 Jan 2023
Stochastic Dimension-reduced Second-order Methods for Policy Optimization Jinsong Liu Chen Xie Qinwen Deng Dongdong Ge Yi-Li Ye 96 1 0 28 Jan 2023
Understanding the Complexity Gains of Single-Task RL with a CurriculumInternational Conference on Machine Learning (ICML), 2022 Qiyang Li Yuexiang Zhai Yi-An Ma Sergey Levine 339 16 0 24 Dec 2022
On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network ParametrizationInternational Conference on Machine Learning (ICML), 2022 Mudit Gaur Vaneet Aggarwal Mridul Agarwal MLT 269 1 0 14 Nov 2022
From Gradient Flow on Population Loss to Learning with Stochastic Gradient DescentNeural Information Processing Systems (NeurIPS), 2022 Satyen Kale Jason D. Lee Chris De Sa Ayush Sekhari Karthik Sridharan 122 5 0 13 Oct 2022
Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated FunctionNeural Information Processing Systems (NeurIPS), 2022 Saeed Masiha Saber Salehkaleybar Niao He Negar Kiyavash Patrick Thiran 270 20 0 25 May 2022
Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization Yuhao Ding Junzi Zhang Hyunin Lee Javad Lavaei 373 23 0 19 Oct 2021
On the Global Optimum Convergence of Momentum-based Policy Gradient Yuhao Ding Junzi Zhang Javad Lavaei 253 25 0 19 Oct 2021