{"total":159,"rows":[{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279,"area":"offlinerl"},{"id":"2102.00135","title":"Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes","created":"2021-01-30","cited_by_count":156,"area":null},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96,"area":null},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84,"area":null},{"id":"2107.11433","title":"A general sample complexity analysis of vanilla policy gradient","created":"2021-07-23","cited_by_count":76,"area":null},{"id":"2503.15477","title":"What Makes a Reward Model a Good Teacher? An Optimization Perspective","created":"2025-03-19","cited_by_count":73,"area":"alignment"},{"id":"2211.07937","title":"An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods","created":"2022-11-15","cited_by_count":68,"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":"2102.11270","title":"Softmax Policy Gradient Methods Can Take Exponential Time to Converge","created":"2021-02-22","cited_by_count":48,"area":null},{"id":"2105.01424","title":"On the Linear convergence of Natural Policy Gradient Algorithm","created":"2021-05-04","cited_by_count":48,"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":"2107.14702","title":"Towards General Function Approximation in Zero-Sum Markov Games","created":"2021-07-30","cited_by_count":43,"area":null},{"id":"2401.15604","title":"Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization","created":"2024-01-28","cited_by_count":42,"area":"diffusion"},{"id":"2101.10506","title":"Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm","created":"2021-01-26","cited_by_count":39,"area":null},{"id":"2109.04024","title":"On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)","created":"2021-09-09","cited_by_count":32,"area":null},{"id":"2210.09921","title":"Finite-time analysis of single-timescale actor-critic","created":"2022-10-18","cited_by_count":32,"area":null},{"id":"2305.18901","title":"Policy Optimization for Continuous Reinforcement Learning","created":"2023-05-30","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":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29,"area":"offlinerl"},{"id":"2108.02731","title":"Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach","created":"2021-08-05","cited_by_count":28,"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":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2109.03699","title":"Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis","created":"2021-09-08","cited_by_count":26,"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":"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":"2302.06205","title":"Order Matters: Agent-by-agent Policy Optimization","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2112.10599","title":"Differentially Private Regret Minimization in Episodic Markov Decision Processes","created":"2021-12-20","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":"2010.08920","title":"Average-reward model-free reinforcement learning: a systematic review and literature mapping","created":"2020-10-18","cited_by_count":22,"area":"alignment"},{"id":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"id":"2201.07052","title":"Differentially Private Reinforcement Learning with Linear Function Approximation","created":"2022-01-18","cited_by_count":22,"area":null},{"id":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","cited_by_count":21,"area":null},{"id":"2201.07296","title":"Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime","created":"2022-01-18","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":"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":"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":"2206.05850","title":"Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm","created":"2022-06-12","cited_by_count":20,"area":null},{"id":"2110.10351","title":"Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process","created":"2021-10-20","cited_by_count":19,"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":"2301.12083","title":"Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic","created":"2023-01-28","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":"2110.11383","title":"Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes","created":"2021-10-21","cited_by_count":17,"area":null},{"id":"2111.02997","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","created":"2021-11-04","cited_by_count":17,"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":"2106.04096","title":"Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation","created":"2021-06-08","cited_by_count":16,"area":null},{"id":"2110.08984","title":"Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs","created":"2021-10-18","cited_by_count":16,"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":"2106.07472","title":"Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation","created":"2021-06-14","cited_by_count":14,"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":"2402.12570","title":"Offline Multi-task Transfer RL with Representational Penalization","created":"2024-02-19","cited_by_count":14,"area":"offlinerl"},{"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":"2006.13506","title":"When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence","created":"2020-06-24","cited_by_count":13,"area":"offlinerl"},{"id":"2104.07794","title":"An $L^2$ Analysis of Reinforcement Learning in High Dimensions with Kernel and Neural Network Approximation","created":"2021-04-15","cited_by_count":13,"area":null},{"id":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2112.10935","title":"Nearly Optimal Policy Optimization with Stable at Any Time Guarantee","created":"2021-12-21","cited_by_count":13,"area":null},{"id":"2202.03334","title":"Policy Optimization for Stochastic Shortest Path","created":"2022-02-07","cited_by_count":13,"area":null},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","cited_by_count":13,"area":"offlinerl"},{"id":"2105.14125","title":"Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2106.08414","title":"On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control","created":"2021-06-15","cited_by_count":12,"area":null},{"id":"2201.05756","title":"Block Policy Mirror Descent","created":"2022-01-15","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":"2103.01391","title":"Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximation","created":"2021-03-02","cited_by_count":10,"area":null},{"id":"2112.14004","title":"Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations","created":"2021-12-28","cited_by_count":10,"area":"offlinerl"},{"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":"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":"2107.06466","title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","created":"2021-07-14","cited_by_count":9,"area":null},{"id":"2306.11455","title":"Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards","created":"2023-06-20","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":"2208.08744","title":"Global Convergence of Two-timescale Actor-Critic for Solving Linear Quadratic Regulator","created":"2022-08-18","cited_by_count":8,"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":"2405.18221","title":"Recurrent Natural Policy Gradient for POMDPs","created":"2024-05-28","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":"2003.03709","title":"Generative Adversarial Imitation Learning with Neural Networks: Global Optimality and Convergence Rate","created":"2020-03-08","cited_by_count":7,"area":"offlinerl"},{"id":"2109.06362","title":"Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2112.13530","title":"Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic","created":"2021-12-27","cited_by_count":7,"area":null},{"id":"2203.11758","title":"Linear convergence of a policy gradient method for some finite horizon continuous time control problems","created":"2022-03-22","cited_by_count":7,"area":null},{"id":"2209.02865","title":"DC-MRTA: Decentralized Multi-Robot Task Allocation and Navigation in Complex Environments","created":"2022-09-07","cited_by_count":7,"area":null},{"id":"2304.12653","title":"Partially Observable Mean Field Multi-Agent Reinforcement Learning Based on Graph-Attention","created":"2023-04-25","cited_by_count":7,"area":null},{"id":"2310.19927","title":"Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms","created":"2023-10-30","cited_by_count":7,"area":null},{"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":"2305.17083","title":"A Policy Gradient Method for Confounded POMDPs","created":"2023-05-26","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":"2403.09940","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":"2406.01853","title":"Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2111.00185","title":"Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings","created":"2021-10-30","cited_by_count":5,"area":null},{"id":"2204.00006","title":"Data Sampling Affects the Complexity of Online SGD over Dependent Data","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2302.03770","title":"Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability","created":"2023-02-07","cited_by_count":5,"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":"2311.02546","title":"On the Second-Order Convergence of Biased Policy Gradient Algorithms","created":"2023-11-05","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null}],"next_cursor":"100"}