{"total":119,"rows":[{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69,"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":"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":"2205.05800","title":"Stochastic first-order methods for average-reward Markov decision processes","created":"2022-05-11","cited_by_count":32,"area":null},{"id":"2209.10579","title":"First-order Policy Optimization for Robust Markov Decision Process","created":"2022-09-21","cited_by_count":32,"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":"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":"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":"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":"2404.03372","title":"Elementary Analysis of Policy Gradient Methods","created":"2024-04-04","cited_by_count":18,"area":"deeprl"},{"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":"2306.11626","title":"Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity","created":"2023-06-20","cited_by_count":17,"area":null},{"id":"2206.02640","title":"Policy Optimization for Markov Games: Unified Framework and Faster Convergence","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2210.08857","title":"On the convergence of policy gradient methods to Nash equilibria in general stochastic games","created":"2022-10-17","cited_by_count":16,"area":null},{"id":"2403.06323","title":"A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents","created":"2024-03-10","cited_by_count":16,"area":"deeprl"},{"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":"2308.14642","title":"Rate-Optimal Policy Optimization for Linear Markov Decision Processes","created":"2023-08-28","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":"2402.17722","title":"Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence","created":"2024-02-27","cited_by_count":11,"area":null},{"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":"2402.17885","title":"Independent Learning in Constrained Markov Potential Games","created":"2024-02-27","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":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2403.06806","title":"On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes","created":"2024-03-11","cited_by_count":9,"area":"deeprl"},{"id":"2309.01107","title":"Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization","created":"2023-09-03","cited_by_count":8,"area":null},{"id":"2310.15418","title":"Fractal Landscapes in Policy Optimization","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2406.01870","title":"Understanding Stochastic Natural Gradient Variational Inference","created":"2024-06-04","cited_by_count":8,"area":null},{"id":"2208.02204","title":"Efficiently Computing Nash Equilibria in Adversarial Team Markov Games","created":"2022-08-03","cited_by_count":7,"area":null},{"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":"2406.19861","title":"Operator World Models for Reinforcement Learning","created":"2024-06-28","cited_by_count":7,"area":"wm"},{"id":"2303.03984","title":"Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization","created":"2023-03-07","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":"2403.14156","title":"Policy Mirror Descent with Lookahead","created":"2024-03-21","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":"2410.04108","title":"On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning","created":"2024-10-05","cited_by_count":6,"area":"offlinerl"},{"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":"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":"2409.19437","title":"Strongly-polynomial time and validation analysis of policy gradient methods","created":"2024-09-28","cited_by_count":5,"area":"deeprl"},{"id":"2410.19933","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","created":"2024-10-25","cited_by_count":5,"area":"alignment"},{"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":"2409.05291","title":"Towards Fast Rates for Federated and Multi-Task Reinforcement Learning","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2510.18340","title":"Why Policy Gradient Algorithms Work for Undiscounted Total-Reward MDPs","created":"2025-10-21","cited_by_count":4,"area":"deeprl"},{"id":"2603.02576","title":"Wasserstein Proximal Policy Gradient","created":"2026-03-03","cited_by_count":4,"area":"deeprl"},{"id":"2208.03247","title":"An Approximate Policy Iteration Viewpoint of Actor-Critic Algorithms","created":"2022-08-05","cited_by_count":3,"area":null},{"id":"2303.12981","title":"Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems","created":"2023-03-23","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":"2405.19811","title":"Approximate Global Convergence of Independent Learning in Multi-Agent Systems","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2407.16602","title":"Functional Acceleration for Policy Mirror Descent","created":"2024-07-23","cited_by_count":3,"area":"deeprl"},{"id":"2409.12882","title":"On the Hardness of Decentralized Multi-Agent Policy Evaluation under Byzantine Attacks","created":"2024-09-19","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":"2503.00229","title":"Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2505.15418","title":"Guided Policy Optimization under Partial Observability","created":"2025-05-21","cited_by_count":3,"area":"deeprl"},{"id":"2506.01597","title":"Policy Newton Algorithm in Reproducing Kernel Hilbert Space","created":"2025-06-02","cited_by_count":3,"area":"deeprl"},{"id":"2507.18059","title":"Multi-Agent Guided Policy Optimization","created":"2025-07-24","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":"2510.19163","title":"Natural Gradient VI: Guarantees for Non-Conjugate Models","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2602.18003","title":"Policy Gradient Algorithms in Average-Reward Multichain MDPs","created":"2026-02-20","cited_by_count":3,"area":"deeprl"},{"id":"2606.16729","title":"Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2305.16621","title":"A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents","created":"2023-05-26","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":"2312.17248","title":"Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity","created":"2023-12-28","cited_by_count":2,"area":"lr"},{"id":"2405.17832","title":"Mollification Effects of Policy Gradient Methods","created":"2024-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2407.03668","title":"Reliable Projection Based Unsupervised Learning for Semi-Definite QCQP with Application of Beamforming Optimization","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2407.10207","title":"Learning to Steer Markovian Agents under Model Uncertainty","created":"2024-07-14","cited_by_count":2,"area":null},{"id":"2410.01195","title":"Stochastic Gradient Descent with Adaptive Data","created":"2024-10-02","cited_by_count":2,"area":"deeprl"},{"id":"2410.01249","title":"Dual Approximation Policy Optimization","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2411.12042","title":"Fast Convergence of Softmax Policy Mirror Ascent","created":"2024-11-18","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":"2505.15342","title":"Policy Testing in Markov Decision Processes","created":"2025-05-21","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":"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":"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":"2312.17194","title":"Resilient Constrained Reinforcement Learning","created":"2023-12-28","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":"2402.05187","title":"Learning mirror maps in policy mirror descent","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2406.05637","title":"A Generalized Version of Chung's Lemma and its Applications","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2411.04913","title":"Structure Matters: Dynamic Policy Gradient","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2504.02130","title":"Ordering-based Conditions for Global Convergence of Policy Gradient Methods","created":"2025-04-02","cited_by_count":1,"area":"deeprl"},{"id":"2506.07054","title":"Policy Gradient with Tree Search: Avoiding Local Optimas through Lookahead","created":"2025-06-08","cited_by_count":1,"area":"deeprl"},{"id":"2506.17828","title":"Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach","created":"2025-06-21","cited_by_count":1,"area":"alignment"},{"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":"2511.16629","title":"Stabilizing Policy Gradient Methods via Reward Profiling","created":"2025-11-20","cited_by_count":1,"area":"deeprl"},{"id":"2602.12181","title":"Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria","created":"2026-02-12","cited_by_count":1,"area":"deeprl"},{"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":"2607.20152","title":"Active Inference as a Convex Markov Decision Process","created":"2026-07-22","cited_by_count":1,"area":"deeprl"},{"id":"2608.05446","title":"EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agents","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2306.10587","title":"Acceleration in Policy Optimization","created":"2023-06-18","cited_by_count":0,"area":null}],"next_cursor":"100"}