{"total":76,"rows":[{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119,"area":null},{"id":"2302.01734","title":"Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies","created":"2023-02-03","cited_by_count":58,"area":null},{"id":"2306.02231","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","created":"2023-06-04","cited_by_count":48,"area":"alignment"},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46,"area":null},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2110.10116","title":"On the Global Optimum Convergence of Momentum-based Policy Gradient","created":"2021-10-19","cited_by_count":26,"area":null},{"id":"2110.10117","title":"Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization","created":"2021-10-19","cited_by_count":25,"area":null},{"id":"2310.11677","title":"Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes","created":"2023-10-18","cited_by_count":25,"area":null},{"id":"2404.08003","title":"Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis","created":"2024-04-09","cited_by_count":21,"area":"deeprl"},{"id":"2205.12856","title":"Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2302.11381","title":"Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes","created":"2023-02-22","cited_by_count":18,"area":null},{"id":"2306.01854","title":"Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space","created":"2023-06-02","cited_by_count":18,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2405.02235","title":"Learning Optimal Deterministic Policies with Stochastic Policy Gradients","created":"2024-05-03","cited_by_count":12,"area":"deeprl"},{"id":"2412.15538","title":"FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF","created":"2024-12-20","cited_by_count":12,"area":"alignment"},{"id":"2507.00445","title":"Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design","created":"2025-07-01","cited_by_count":11,"area":"diffusion"},{"id":"2508.02833","title":"TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback","created":"2025-08-04","cited_by_count":11,"area":"lr"},{"id":"2312.00561","title":"A safe exploration approach to constrained Markov decision processes","created":"2023-12-01","cited_by_count":10,"area":null},{"id":"2402.17235","title":"Stochastic Gradient Succeeds for Bandits","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2405.05630","title":"Policy Gradient with Active Importance Sampling","created":"2024-05-09","cited_by_count":10,"area":"deeprl"},{"id":"2310.02671","title":"Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods","created":"2023-10-04","cited_by_count":9,"area":null},{"id":"2402.02042","title":"Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm","created":"2024-02-03","cited_by_count":9,"area":"deeprl"},{"id":"2410.12455","title":"Loss Landscape Characterization of Neural Networks without Over-Parametrization","created":"2024-10-16","cited_by_count":8,"area":null},{"id":"2602.21189","title":"Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2405.13136","title":"Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs","created":"2024-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2411.00401","title":"Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory","created":"2024-11-01","cited_by_count":7,"area":"deeprl"},{"id":"2505.19986","title":"Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach","created":"2025-05-26","cited_by_count":7,"area":"deeprl"},{"id":"2401.01084","title":"Global Convergence of Natural Policy Gradient with Hessian-aided Momentum Variance Reduction","created":"2024-01-02","cited_by_count":6,"area":"deeprl"},{"id":"2403.08955","title":"Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis","created":"2024-03-13","cited_by_count":6,"area":"deeprl"},{"id":"2403.09940","title":"Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries","created":"2024-03-15","cited_by_count":6,"area":"deeprl"},{"id":"2512.20576","title":"Performative Policy Gradient: Optimality in Performative Reinforcement Learning","created":"2025-12-23","cited_by_count":6,"area":"deeprl"},{"id":"2210.06705","title":"From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent","created":"2022-10-13","cited_by_count":5,"area":null},{"id":"2311.02546","title":"On the Second-Order Convergence of Biased Policy Gradient Algorithms","created":"2023-11-05","cited_by_count":5,"area":null},{"id":"2405.13592","title":"Almost sure convergence rates of stochastic gradient methods under gradient domination","created":"2024-05-22","cited_by_count":5,"area":"deeprl"},{"id":"2409.05291","title":"Towards Fast Rates for Federated and Multi-Task Reinforcement Learning","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2502.07141","title":"Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2211.07675","title":"On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization","created":"2022-11-14","cited_by_count":3,"area":null},{"id":"2305.15249","title":"Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2410.08868","title":"On the Convergence of Single-Timescale Actor-Critic","created":"2024-10-11","cited_by_count":3,"area":"deeprl"},{"id":"2410.15610","title":"On The Global Convergence Of Online RLHF With Neural Parametrization","created":"2024-10-21","cited_by_count":3,"area":"alignment"},{"id":"2412.16561","title":"A learning-based approach to stochastic optimal control under reach-avoid constraint","created":"2024-12-21","cited_by_count":3,"area":"deeprl"},{"id":"2509.18822","title":"On the Convergence of Policy Mirror Descent with Temporal Difference Evaluation","created":"2025-09-23","cited_by_count":3,"area":"deeprl"},{"id":"2510.21060","title":"On the Sample Complexity of Differentially Private Policy Optimization","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2602.16012","title":"Towards Efficient Constraint Handling in Neural Solvers for Routing Problems","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2305.19575","title":"On the Linear Convergence of Policy Gradient under Hadamard Parameterization","created":"2023-05-31","cited_by_count":2,"area":null},{"id":"2402.02569","title":"On the Complexity of Finite-Sum Smooth Optimization under the Polyak-{\\L}ojasiewicz Condition","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2407.10775","title":"Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning","created":"2024-07-15","cited_by_count":2,"area":"deeprl"},{"id":"2410.01195","title":"Stochastic Gradient Descent with Adaptive Data","created":"2024-10-02","cited_by_count":2,"area":"deeprl"},{"id":"2502.11033","title":"Convergence of Policy Mirror Descent Beyond Compatible Function Approximation","created":"2025-02-16","cited_by_count":2,"area":null},{"id":"2512.16565","title":"Non-Asymptotic Global Convergence of PPO-Clip","created":"2025-12-18","cited_by_count":2,"area":null},{"id":"2512.24056","title":"Policy Mirror Descent with Temporal Difference Learning: Sample Complexity under Online Markov Data","created":"2025-12-30","cited_by_count":2,"area":"deeprl"},{"id":"2601.18626","title":"Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learning","created":"2026-01-26","cited_by_count":2,"area":"deeprl"},{"id":"2401.12508","title":"On the Stochastic (Variance-Reduced) Proximal Gradient Method for Regularized Expected Reward Optimization","created":"2024-01-23","cited_by_count":1,"area":"deeprl"},{"id":"2411.04913","title":"Structure Matters: Dynamic Policy Gradient","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2506.06178","title":"Reusing Trajectories in Policy Gradients Enables Fast Convergence","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2507.04406","title":"Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning","created":"2025-07-06","cited_by_count":1,"area":"deeprl"},{"id":"2509.24305","title":"Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning","created":"2025-09-29","cited_by_count":1,"area":"deeprl"},{"id":"2603.15001","title":"How Log-Barrier Helps Exploration in Policy Optimization","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2603.26547","title":"A Lyapunov Analysis of Softmax Policy Gradient for Stochastic Bandits","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2605.10909","title":"Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy Gradients","created":"2026-05-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.24357","title":"Refined Analysis of Entropy-Regularized Actor-Critic","created":"2026-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2608.03562","title":"Robust General Utility for Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2610.03165","title":"Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds","created":"2026-10-02","cited_by_count":1,"area":"deeprl"},{"id":"2301.12174","title":"Stochastic Dimension-reduced Second-order Methods for Policy Optimization","created":"2023-01-28","cited_by_count":0,"area":null},{"id":"2308.10630","title":"A Homogenization Approach for Gradient-Dominated Stochastic Optimization","created":"2023-08-21","cited_by_count":0,"area":null},{"id":"2403.01605","title":"Towards Provable Log Density Policy Gradient","created":"2024-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2407.04264","title":"Langevin Dynamics: A Unified Perspective on Optimization via Lyapunov Potentials","created":"2024-07-05","cited_by_count":0,"area":null},{"id":"2505.18433","title":"Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2508.17218","title":"Learning Graph-Indexed Trajectory Patterns for Stochastic On-Time Arrival Routing","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2510.02735","title":"Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2601.21523","title":"Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.01505","title":"Optimal Sample Complexity for Single Time-Scale Actor-Critic with Momentum","created":"2026-02-02","cited_by_count":0,"area":"deeprl"},{"id":"2605.18675","title":"COOPO: Cyclic Offline-Online Policy Optimization Algorithm","created":"2026-05-18","cited_by_count":0,"area":"offlinerl"},{"id":"2605.27900","title":"Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning","created":"2026-05-27","cited_by_count":0,"area":"mllm"},{"id":"2610.01399","title":"Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.13692","title":"Variance-Reduced Policy Gradient is Nearly Minimax-Optimal","created":"2026-10-09","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}