{"total":177,"rows":[{"id":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427,"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":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187,"area":"alignment"},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"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":"2101.04233","title":"Independent Policy Gradient Methods for Competitive Reinforcement Learning","created":"2021-01-11","cited_by_count":101,"area":null},{"id":"2106.01969","title":"Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games","created":"2021-06-03","cited_by_count":93,"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":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2007.08202","title":"Provably Good Batch Reinforcement Learning Without Great Exploration","created":"2020-07-16","cited_by_count":77,"area":"offlinerl"},{"id":"2102.08607","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","created":"2021-02-17","cited_by_count":70,"area":null},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53,"area":null},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52,"area":null},{"id":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"id":"2306.11816","title":"Learning to Generate Better Than Your LLM","created":"2023-06-20","cited_by_count":49,"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":"2105.06072","title":"Leveraging Non-uniformity in First-order Non-convex Optimization","created":"2021-05-13","cited_by_count":44,"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":"2102.11941","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","created":"2021-02-23","cited_by_count":40,"area":null},{"id":"2308.02585","title":"PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback","created":"2023-08-03","cited_by_count":40,"area":"alignment"},{"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":"2110.10614","title":"Independent Natural Policy Gradient Always Converges in Markov Potential Games","created":"2021-10-20","cited_by_count":37,"area":null},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"id":"2210.09921","title":"Finite-time analysis of single-timescale actor-critic","created":"2022-10-18","cited_by_count":32,"area":null},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"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":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2105.08024","title":"Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting","created":"2021-05-17","cited_by_count":28,"area":null},{"id":"2110.08847","title":"Provable RL with Exogenous Distractors via Multistep Inverse Dynamics","created":"2021-10-17","cited_by_count":28,"area":null},{"id":"2102.00582","title":"Multi-Agent Reinforcement Learning with Temporal Logic Specifications","created":"2021-02-01","cited_by_count":27,"area":null},{"id":"2302.03673","title":"Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation","created":"2023-02-07","cited_by_count":27,"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":"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":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"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":"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":"2003.03924","title":"Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison","created":"2020-03-09","cited_by_count":22,"area":"offlinerl"},{"id":"2106.13781","title":"Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems","created":"2021-06-25","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":"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":"2211.17116","title":"Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning","created":"2022-11-30","cited_by_count":20,"area":null},{"id":"2406.15567","title":"SAIL: Self-Improving Efficient Online Alignment of Large Language Models","created":"2024-06-21","cited_by_count":20,"area":"alignment"},{"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":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2102.08903","title":"Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games","created":"2021-02-17","cited_by_count":18,"area":null},{"id":"2102.11055","title":"Escaping from Zero Gradient: Revisiting Action-Constrained Reinforcement Learning via Frank-Wolfe Policy Optimization","created":"2021-02-22","cited_by_count":18,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2110.15572","title":"Understanding the Effect of Stochasticity in Policy Optimization","created":"2021-10-29","cited_by_count":18,"area":null},{"id":"2202.04970","title":"Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory","created":"2022-02-10","cited_by_count":18,"area":null},{"id":"2205.13746","title":"Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games","created":"2022-05-27","cited_by_count":18,"area":null},{"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":"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":"2206.10414","title":"A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences","created":"2022-06-21","cited_by_count":17,"area":null},{"id":"2302.09408","title":"Best of Both Worlds Policy Optimization","created":"2023-02-18","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":"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":"2206.05357","title":"Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning","created":"2022-06-10","cited_by_count":15,"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":"2202.05195","title":"Uncovering Instabilities in Variational-Quantum Deep Q-Networks","created":"2022-02-10","cited_by_count":14,"area":null},{"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":"2208.01899","title":"Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis","created":"2022-08-03","cited_by_count":13,"area":"offlinerl"},{"id":"2303.04386","title":"Policy Mirror Descent Inherently Explores Action Space","created":"2023-03-08","cited_by_count":13,"area":null},{"id":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","cited_by_count":13,"area":null},{"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":"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":"2201.05756","title":"Block Policy Mirror Descent","created":"2022-01-15","cited_by_count":11,"area":null},{"id":"2201.12332","title":"On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces","created":"2022-01-28","cited_by_count":11,"area":null},{"id":"2102.06234","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","created":"2021-02-11","cited_by_count":10,"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":"2302.13144","title":"Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient","created":"2023-02-25","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":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10,"area":"offlinerl"},{"id":"2110.04638","title":"Satisficing Paths and Independent Multi-Agent Reinforcement Learning in Stochastic Games","created":"2021-10-09","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":"2405.20860","title":"Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation","created":"2024-05-31","cited_by_count":9,"area":"deeprl"},{"id":"2103.05981","title":"Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme","created":"2021-03-10","cited_by_count":8,"area":null},{"id":"2111.02994","title":"Towards an Understanding of Default Policies in Multitask Policy Optimization","created":"2021-11-04","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":"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":"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":"2208.02204","title":"Efficiently Computing Nash Equilibria in Adversarial Team Markov Games","created":"2022-08-03","cited_by_count":7,"area":null},{"id":"2304.10951","title":"A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning","created":"2023-04-21","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":"2408.17380","title":"Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory control","created":"2024-08-30","cited_by_count":7,"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":"2511.03618","title":"Towards Formalizing Reinforcement Learning Theory: A Robbins-Siegmund Approach","created":"2025-11-05","cited_by_count":7,"area":"deeprl"},{"id":"2106.07814","title":"Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity","created":"2021-06-15","cited_by_count":6,"area":null}],"next_cursor":"100"}