{"total":120,"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":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269,"area":"offlinerl"},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151,"area":"offlinerl"},{"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":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2110.08695","title":"Towards Instance-Optimal Offline Reinforcement Learning with Pessimism","created":"2021-10-17","cited_by_count":78,"area":"offlinerl"},{"id":"2305.18438","title":"Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism","created":"2023-05-29","cited_by_count":69,"area":"alignment"},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66,"area":"offlinerl"},{"id":"2203.05804","title":"Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism","created":"2022-03-11","cited_by_count":65,"area":"offlinerl"},{"id":"2506.00613","title":"WorldGym: World Model as An Environment for Policy Evaluation","created":"2025-05-31","cited_by_count":64,"area":"wm"},{"id":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62,"area":"offlinerl"},{"id":"2102.01748","title":"Near-Optimal Offline Reinforcement Learning via Double Variance Reduction","created":"2021-02-02","cited_by_count":56,"area":"offlinerl"},{"id":"2205.15512","title":"Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game","created":"2022-05-31","cited_by_count":55,"area":"offlinerl"},{"id":"2202.07511","title":"Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets","created":"2022-02-15","cited_by_count":44,"area":null},{"id":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40,"area":"offlinerl"},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38,"area":"offlinerl"},{"id":"2103.14077","title":"Nearly Horizon-Free Offline Reinforcement Learning","created":"2021-03-25","cited_by_count":36,"area":"offlinerl"},{"id":"2206.12020","title":"Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems","created":"2022-06-24","cited_by_count":35,"area":null},{"id":"2106.11960","title":"Variance-Aware Off-Policy Evaluation with Linear Function Approximation","created":"2021-06-22","cited_by_count":34,"area":null},{"id":"2201.06169","title":"On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation","created":"2022-01-17","cited_by_count":33,"area":null},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2105.03863","title":"Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics","created":"2021-05-09","cited_by_count":27,"area":null},{"id":"2102.00479","title":"Fast Rates for the Regret of Offline Reinforcement Learning","created":"2021-01-31","cited_by_count":26,"area":"offlinerl"},{"id":"2106.03207","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage","created":"2021-06-06","cited_by_count":26,"area":"offlinerl"},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2111.13807","title":"Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization","created":"2021-11-27","cited_by_count":25,"area":"offlinerl"},{"id":"2011.04019","title":"Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient","created":"2020-11-08","cited_by_count":24,"area":"offlinerl"},{"id":"2403.13219","title":"Diffusion Model for Data-Driven Black-Box Optimization","created":"2024-03-20","cited_by_count":24,"area":"diffusion"},{"id":"2211.13208","title":"On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation","created":"2022-11-23","cited_by_count":22,"area":"offlinerl"},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21,"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":"2403.09621","title":"Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning","created":"2024-03-14","cited_by_count":18,"area":"offlinerl"},{"id":"2207.05837","title":"Learning Bellman Complete Representations for Offline Policy Evaluation","created":"2022-07-12","cited_by_count":17,"area":"offlinerl"},{"id":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17,"area":null},{"id":"2302.10160","title":"Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift","created":"2023-02-20","cited_by_count":17,"area":null},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2405.19883","title":"From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems","created":"2024-05-30","cited_by_count":17,"area":null},{"id":"2102.10242","title":"Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach","created":"2021-02-20","cited_by_count":16,"area":null},{"id":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2405.02181","title":"Imitation Learning in Discounted Linear MDPs without exploration assumptions","created":"2024-05-03","cited_by_count":15,"area":"offlinerl"},{"id":"2105.06029","title":"Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings","created":"2021-05-13","cited_by_count":14,"area":"offlinerl"},{"id":"2109.03970","title":"PowerGym: A Reinforcement Learning Environment for Volt-Var Control in Power Distribution Systems","created":"2021-09-08","cited_by_count":14,"area":null},{"id":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","cited_by_count":14,"area":"offlinerl"},{"id":"2206.05581","title":"Federated Offline Reinforcement Learning","created":"2022-06-11","cited_by_count":13,"area":"offlinerl"},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2211.02016","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","created":"2022-11-03","cited_by_count":13,"area":"offlinerl"},{"id":"2206.02887","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2211.16583","title":"Offline Policy Evaluation and Optimization under Confounding","created":"2022-11-29","cited_by_count":12,"area":"offlinerl"},{"id":"2402.08991","title":"Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption","created":"2024-02-14","cited_by_count":12,"area":"deeprl"},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2103.05741","title":"Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds","created":"2021-03-09","cited_by_count":11,"area":null},{"id":"2108.08765","title":"Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation","created":"2021-08-19","cited_by_count":11,"area":"offlinerl"},{"id":"2112.12320","title":"Model Selection in Batch Policy Optimization","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2103.09847","title":"Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm","created":"2021-03-17","cited_by_count":10,"area":"offlinerl"},{"id":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10,"area":"offlinerl"},{"id":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2405.18520","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","created":"2024-05-28","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":"2101.07781","title":"Minimax Off-Policy Evaluation for Multi-Armed Bandits","created":"2021-01-19","cited_by_count":9,"area":null},{"id":"2110.12468","title":"False Correlation Reduction for Offline Reinforcement Learning","created":"2021-10-24","cited_by_count":9,"area":"offlinerl"},{"id":"2208.11040","title":"Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instruments","created":"2022-08-23","cited_by_count":9,"area":"offlinerl"},{"id":"2006.03886","title":"Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning","created":"2020-06-06","cited_by_count":8,"area":"offlinerl"},{"id":"2103.06671","title":"Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks","created":"2021-03-11","cited_by_count":8,"area":"offlinerl"},{"id":"2210.15543","title":"Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions","created":"2022-10-27","cited_by_count":8,"area":null},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2203.04236","title":"A Complete Characterization of Linear Estimators for Offline Policy Evaluation","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2209.10444","title":"Off-Policy Risk Assessment in Markov Decision Processes","created":"2022-09-21","cited_by_count":7,"area":null},{"id":"2306.10694","title":"On the Model-Misspecification in Reinforcement Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2310.18715","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","created":"2023-10-28","cited_by_count":7,"area":"offlinerl"},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2304.02574","title":"Conformal Off-Policy Evaluation in Markov Decision Processes","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6,"area":null},{"id":"2401.03301","title":"On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling, and Beyond","created":"2024-01-06","cited_by_count":6,"area":"offlinerl"},{"id":"2402.15739","title":"Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery","created":"2024-02-24","cited_by_count":6,"area":null},{"id":"2407.07631","title":"Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning","created":"2024-07-10","cited_by_count":6,"area":"offlinerl"},{"id":"2408.04526","title":"Hybrid Reinforcement Learning Breaks Sample Size Barriers in Linear MDPs","created":"2024-08-08","cited_by_count":6,"area":"offlinerl"},{"id":"2210.07536","title":"A Reinforcement Learning Approach to Estimating Long-term Treatment Effects","created":"2022-10-14","cited_by_count":5,"area":null},{"id":"2310.06268","title":"Bi-Level Offline Policy Optimization with Limited Exploration","created":"2023-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2411.14341","title":"Logarithmic Neyman Regret for Adaptive Estimation of the Average Treatment Effect","created":"2024-11-21","cited_by_count":4,"area":"deeprl"},{"id":"2206.04921","title":"Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2212.01925","title":"Counterfactual Learning with General Data-generating Policies","created":"2022-12-04","cited_by_count":3,"area":null},{"id":"2305.13289","title":"Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach","created":"2023-05-22","cited_by_count":3,"area":"offlinerl"},{"id":"2307.13332","title":"The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2401.05233","title":"Taming \"data-hungry\" reinforcement learning? Stability in continuous state-action spaces","created":"2024-01-10","cited_by_count":3,"area":"deeprl"},{"id":"2405.16809","title":"Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\\pi$-Realizability and Concentrability","created":"2024-05-27","cited_by_count":3,"area":"offlinerl"},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"id":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2505.21395","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment","created":"2025-05-27","cited_by_count":3,"area":"alignment"},{"id":"2110.02421","title":"Explaining Off-Policy Actor-Critic From A Bias-Variance Perspective","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2210.11377","title":"Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces","created":"2022-10-20","cited_by_count":2,"area":null},{"id":"2303.11187","title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2310.01616","title":"Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity","created":"2023-10-02","cited_by_count":2,"area":"offlinerl"},{"id":"2404.00195","title":"Multiple-policy Evaluation via Density Estimation","created":"2024-03-29","cited_by_count":2,"area":null},{"id":"2408.12307","title":"Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning","created":"2024-08-22","cited_by_count":2,"area":"offlinerl"},{"id":"2502.04673","title":"Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2510.17391","title":"Finite-Time Bounds for Average-Reward Fitted Q-Iteration","created":"2025-10-20","cited_by_count":2,"area":"offlinerl"},{"id":"2111.11758","title":"The Impact of Data Distribution on Q-learning with Function Approximation","created":"2021-11-23","cited_by_count":1,"area":null}],"next_cursor":"100"}