{"total":58,"rows":[{"id":"2410.13849","title":"From Gradient Clipping to Normalization for Heavy Tailed SGD","created":"2024-10-17","cited_by_count":49,"area":null},{"id":"2311.03252","title":"Parameter-Agnostic Optimization under Relaxed Smoothness","created":"2023-11-06","cited_by_count":29,"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":"2305.12475","title":"Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods","created":"2023-05-21","cited_by_count":23,"area":null},{"id":"2310.02951","title":"A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces","created":"2023-10-04","cited_by_count":23,"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":"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":"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":"2402.17722","title":"Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence","created":"2024-02-27","cited_by_count":11,"area":null},{"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":"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":"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":"2410.12455","title":"Loss Landscape Characterization of Neural Networks without Over-Parametrization","created":"2024-10-16","cited_by_count":8,"area":null},{"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":"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":"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":"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":"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":"2410.15610","title":"On The Global Convergence Of Online RLHF With Neural Parametrization","created":"2024-10-21","cited_by_count":3,"area":"alignment"},{"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":"2510.10690","title":"Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits","created":"2025-10-12","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":"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":"2510.12334","title":"Finite-time Convergence Analysis of Actor-Critic with Evolving Reward","created":"2025-10-14","cited_by_count":2,"area":"deeprl"},{"id":"2511.14501","title":"Improved Convergence in Parameter-Agnostic Error Feedback through Momentum","created":"2025-11-18","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":"2603.08518","title":"Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning","created":"2026-03-09","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":"2408.11513","title":"Last-Iterate Convergence of General Parameterized Policies in Constrained MDPs","created":"2024-08-21","cited_by_count":1,"area":"deeprl"},{"id":"2506.06178","title":"Reusing Trajectories in Policy Gradients Enables Fast Convergence","created":"2025-06-06","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":"2510.19199","title":"A Communication-Efficient Decentralized Actor-Critic Algorithm","created":"2025-10-22","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":"2605.24357","title":"Refined Analysis of Entropy-Regularized Actor-Critic","created":"2026-05-23","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":"2405.11727","title":"Highway Graph to Accelerate Reinforcement Learning","created":"2024-05-20","cited_by_count":0,"area":"deeprl"},{"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":"2509.10077","title":"Predictive Spike Timing Enables Distributed Shortest Path Computation in Spiking Neural Networks","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2602.06567","title":"Markov Decision Processes of the Third Kind: Learning Distributions by Policy Gradient Descent","created":"2026-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2604.28144","title":"Global Optimality for Constrained Exploration via Penalty Regularization","created":"2026-04-30","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":"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"},{"id":"2610.13711","title":"Towards Understanding the Training of GFlowNets: A Theoretical Perspective","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}