{"total":84,"rows":[{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119,"area":null},{"id":"2105.15186","title":"Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization","created":"2021-05-31","cited_by_count":63,"area":null},{"id":"2202.04129","title":"Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence","created":"2022-02-08","cited_by_count":57,"area":null},{"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":"2402.06886","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","created":"2024-02-10","cited_by_count":41,"area":"alignment"},{"id":"2205.05800","title":"Stochastic first-order methods for average-reward Markov decision processes","created":"2022-05-11","cited_by_count":32,"area":null},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"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":"2410.04612","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","created":"2024-10-06","cited_by_count":30,"area":"alignment"},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28,"area":null},{"id":"2210.01050","title":"Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games","created":"2022-10-03","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":"2111.00552","title":"Policy Optimization for Constrained MDPs with Provable Fast Global Convergence","created":"2021-10-31","cited_by_count":23,"area":null},{"id":"2211.16715","title":"Policy Optimization over General State and Action Spaces","created":"2022-11-30","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":"2206.00833","title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm","created":"2022-06-02","cited_by_count":20,"area":null},{"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":"2106.12112","title":"Bregman Gradient Policy Optimization","created":"2021-06-23","cited_by_count":17,"area":null},{"id":"2209.15382","title":"Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2301.13087","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","created":"2023-01-30","cited_by_count":17,"area":null},{"id":"2201.09457","title":"Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity","created":"2022-01-24","cited_by_count":14,"area":null},{"id":"2303.04386","title":"Policy Mirror Descent Inherently Explores Action Space","created":"2023-03-08","cited_by_count":13,"area":null},{"id":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2405.20250","title":"Entropy annealing for policy mirror descent in continuous time and space","created":"2024-05-30","cited_by_count":12,"area":null},{"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":"2204.05466","title":"Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization","created":"2022-04-12","cited_by_count":10,"area":null},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","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":"2210.12812","title":"Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence","created":"2022-10-23","cited_by_count":8,"area":null},{"id":"2210.11201","title":"Robust Imitation via Mirror Descent Inverse Reinforcement Learning","created":"2022-10-20","cited_by_count":6,"area":"offlinerl"},{"id":"2310.01706","title":"On Representation Complexity of Model-based and Model-free Reinforcement Learning","created":"2023-10-03","cited_by_count":6,"area":null},{"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":"2408.08075","title":"Independent Policy Mirror Descent for Markov Potential Games: Scaling to Large Number of Players","created":"2024-08-15","cited_by_count":6,"area":"deeprl"},{"id":"2410.01101","title":"Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank","created":"2024-10-01","cited_by_count":6,"area":"offlinerl"},{"id":"2403.19448","title":"Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients","created":"2024-03-28","cited_by_count":5,"area":"deeprl"},{"id":"2406.08847","title":"Roping in Uncertainty: Robustness and Regularization in Markov Games","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2408.05885","title":"GFlowNet Training by Policy Gradients","created":"2024-08-12","cited_by_count":5,"area":"deeprl"},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"area":"deeprl"},{"id":"2206.01666","title":"Algorithm for Constrained Markov Decision Process with Linear Convergence","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2506.03757","title":"PPO in the Fisher-Rao geometry","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2110.02398","title":"Approximate Newton policy gradient algorithms","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2412.01630","title":"Review of Mathematical Optimization in Federated Learning","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2502.09780","title":"Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games","created":"2025-02-13","cited_by_count":3,"area":null},{"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":"2202.10506","title":"Accelerating Primal-dual Methods for Regularized Markov Decision Processes","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2211.15880","title":"Mirror descent of Hopfield model","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2301.13006","title":"Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods","created":"2023-01-30","cited_by_count":2,"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":"2310.05230","title":"Global Convergence of Policy Gradient Methods in Reinforcement Learning, Games and Control","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2410.01249","title":"Dual Approximation Policy Optimization","created":"2024-10-02","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":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","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":"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":"2205.08176","title":"On the Convergence of Policy in Unregularized Policy Mirror Descent","created":"2022-05-17","cited_by_count":1,"area":null},{"id":"2301.08442","title":"Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning","created":"2023-01-20","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":"2406.04163","title":"Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes","created":"2024-06-06","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":"2411.19193","title":"Convex Regularization and Convergence of Policy Gradient Flows under Safety Constraints","created":"2024-11-28","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":"2507.08718","title":"On the Effect of Regularization in Policy Mirror Descent","created":"2025-07-11","cited_by_count":1,"area":"deeprl"},{"id":"2509.01432","title":"The Geometry of Nonlinear Reinforcement Learning","created":"2025-09-01","cited_by_count":1,"area":"deeprl"},{"id":"2602.10894","title":"Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games","created":"2026-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2603.10199","title":"Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces","created":"2026-03-10","cited_by_count":1,"area":"deeprl"},{"id":"2603.17875","title":"Operator-Theoretic Foundations and Policy Gradient Methods for General MDPs with Unbounded Costs","created":"2026-03-18","cited_by_count":1,"area":"deeprl"},{"id":"2604.06039","title":"Value Mirror Descent for Reinforcement Learning","created":"2026-04-07","cited_by_count":1,"area":"deeprl"},{"id":"2605.02469","title":"Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2607.28560","title":"X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching","created":"2026-07-30","cited_by_count":1,"area":"diffusion"},{"id":"2609.13564","title":"When Greedy Sampling Explores: KL-Regularized Contextual Bandits without Eluder-Dimension Dependence","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2410.05127","title":"Last Iterate Convergence in Monotone Mean Field Games","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2511.05640","title":"Blind Inverse Game Theory: Jointly Decoding Rewards and Rationality in Entropy-Regularized Competitive Games","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2602.05933","title":"Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.12838","title":"A New Kernel Regularity Condition for Distributed Mirror Descent: Broader Coverage and Simpler Analysis","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.17527","title":"Mirror Descent on Riemannian Manifolds","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2605.10671","title":"Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2606.29092","title":"Priced Motion Through Optimal Faces: A Normal-Fan Geometry for Non-Stationary Adversarial MDPs","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.22982","title":"Finite-Time Analysis of the Natural Policy Gradient in Finite-Horizon Markov Decision Processes","created":"2026-07-25","cited_by_count":0,"area":"deeprl"},{"id":"2609.35466","title":"An analysis of Mirror-Descent Soft Actor-Critic","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2609.39837","title":"Fast Regularized Policy Mirror Descent with One-Step TD Updates","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04117","title":"Sharp Convergence and Sample Complexity of Policy Mirror Descent for Average-Reward MDPs","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}