{"total":68,"rows":[{"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":"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":"2309.01922","title":"Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes","created":"2023-09-05","cited_by_count":26,"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":"2310.19807","title":"Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates","created":"2023-10-09","cited_by_count":21,"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":"2412.18164","title":"Stochastic Control for Fine-tuning Diffusion Models: Optimality, Regularity, and Convergence","created":"2024-12-24","cited_by_count":19,"area":"diffusion"},{"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":"2312.12065","title":"PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping","created":"2023-12-19","cited_by_count":17,"area":null},{"id":"2407.18878","title":"A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach","created":"2024-07-26","cited_by_count":15,"area":"deeprl"},{"id":"2404.02108","title":"Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs","created":"2024-04-02","cited_by_count":14,"area":"deeprl"},{"id":"2405.02235","title":"Learning Optimal Deterministic Policies with Stochastic Policy Gradients","created":"2024-05-03","cited_by_count":12,"area":"deeprl"},{"id":"2405.10624","title":"Sample-Efficient Constrained Reinforcement Learning with General Parameterization","created":"2024-05-17","cited_by_count":11,"area":"deeprl"},{"id":"2312.00561","title":"A safe exploration approach to constrained Markov decision processes","created":"2023-12-01","cited_by_count":10,"area":null},{"id":"2503.17644","title":"On The Sample Complexity Bounds In Bilevel Reinforcement Learning","created":"2025-03-22","cited_by_count":10,"area":"deeprl"},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","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":"2301.06889","title":"Mean-Field Control based Approximation of Multi-Agent Reinforcement Learning in Presence of a Non-decomposable Shared Global State","created":"2023-01-13","cited_by_count":8,"area":null},{"id":"2305.15546","title":"Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2405.18221","title":"Recurrent Natural Policy Gradient for POMDPs","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2405.19499","title":"Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments","created":"2024-05-29","cited_by_count":8,"area":"deeprl"},{"id":"2505.15138","title":"Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm","created":"2025-05-21","cited_by_count":8,"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":"2403.09940","title":"Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries","created":"2024-03-15","cited_by_count":6,"area":"deeprl"},{"id":"2403.11925","title":"Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles","created":"2024-03-18","cited_by_count":6,"area":"deeprl"},{"id":"2406.10576","title":"Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient","created":"2024-06-15","cited_by_count":6,"area":null},{"id":"2505.19238","title":"Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees","created":"2025-05-25","cited_by_count":6,"area":"deeprl"},{"id":"2303.08431","title":"Policy Gradient Converges to the Globally Optimal Policy for Nearly Linear-Quadratic Regulators","created":"2023-03-15","cited_by_count":5,"area":null},{"id":"2306.10486","title":"On the Global Convergence of Natural Actor-Critic with Two-layer Neural Network Parametrization","created":"2023-06-18","cited_by_count":5,"area":null},{"id":"2310.11897","title":"Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning","created":"2023-10-18","cited_by_count":4,"area":null},{"id":"2501.16243","title":"Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach","created":"2025-01-27","cited_by_count":4,"area":"deeprl"},{"id":"2502.15968","title":"Enhancing PPO with Trajectory-Aware Hybrid Policies","created":"2025-02-21","cited_by_count":4,"area":"deeprl"},{"id":"2602.08000","title":"Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization","created":"2026-02-08","cited_by_count":4,"area":"deeprl"},{"id":"2301.13236","title":"Policy Gradient with Tree Expansion","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2309.13681","title":"Accelerating Large Batch Training via Gradient Signal to Noise Ratio (GSNR)","created":"2023-09-24","cited_by_count":3,"area":null},{"id":"2408.04780","title":"Learning in Herding Mean Field Games: Single-Loop Algorithm with Finite-Time Convergence Analysis","created":"2024-08-08","cited_by_count":3,"area":"deeprl"},{"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":"2603.06957","title":"Post-Training with Policy Gradients: Optimality and the Base Model Barrier","created":"2026-03-07","cited_by_count":3,"area":"deeprl"},{"id":"2309.10679","title":"Oracle Complexity Reduction for Model-free LQR: A Stochastic Variance-Reduced Policy Gradient Approach","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2502.11033","title":"Convergence of Policy Mirror Descent Beyond Compatible Function Approximation","created":"2025-02-16","cited_by_count":2,"area":null},{"id":"2510.12334","title":"Finite-time Convergence Analysis of Actor-Critic with Evolving Reward","created":"2025-10-14","cited_by_count":2,"area":"deeprl"},{"id":"2512.16565","title":"Non-Asymptotic Global Convergence of PPO-Clip","created":"2025-12-18","cited_by_count":2,"area":null},{"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":"2603.08518","title":"Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"deeprl"},{"id":"2212.05237","title":"Coordinate Ascent for Off-Policy RL with Global Convergence Guarantees","created":"2022-12-10","cited_by_count":1,"area":null},{"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":"2405.02769","title":"Linear Convergence of Independent Natural Policy Gradient in Games with Entropy Regularization","created":"2024-05-04","cited_by_count":1,"area":"deeprl"},{"id":"2408.11513","title":"Last-Iterate Convergence of General Parameterized Policies in Constrained MDPs","created":"2024-08-21","cited_by_count":1,"area":"deeprl"},{"id":"2602.11387","title":"Provably Efficient Algorithms for S- and Non-Rectangular Robust MDPs with General Parameterization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.07698","title":"Global Convergence of Average Reward Constrained MDPs with Neural Critic and General Policy Parameterization","created":"2026-03-08","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":"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":"2606.31524","title":"On the Convergence of Self-Improving Online LLM Alignment","created":"2026-06-30","cited_by_count":1,"area":"alignment"},{"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":"2305.11017","title":"Deep Metric Tensor Regularized Policy Gradient","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2405.12228","title":"Fast Stochastic Policy Gradient: Negative Momentum for Reinforcement Learning","created":"2024-05-08","cited_by_count":0,"area":"deeprl"},{"id":"2509.15981","title":"Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations","created":"2025-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2606.25012","title":"Bias-Controlled Primal-Dual Natural Actor-Critic: Optimal Rates for Constrained Multi-Objective Average-Reward RL","created":"2026-06-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.28390","title":"Hierarchical Multilevel Monte Carlo for Order-Optimal Neural Actor-Critic in Average-Reward CMDPs","created":"2026-07-30","cited_by_count":0,"area":"deeprl"},{"id":"2607.28849","title":"Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity","created":"2026-07-30","cited_by_count":0,"area":"alignment"},{"id":"2610.13692","title":"Variance-Reduced Policy Gradient is Nearly Minimax-Optimal","created":"2026-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2610.13711","title":"Towards Understanding the Training of GFlowNets: A Theoretical Perspective","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14041","title":"A Geometric Perspective on Reward Function Updates in Inverse Reinforcement Learning","created":"2026-10-02","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}