{"total":227,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662,"area":"offlinerl"},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"id":"2010.11895","title":"What are the Statistical Limits of Offline RL with Linear Function Approximation?","created":"2020-10-22","cited_by_count":136,"area":"offlinerl"},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123,"area":"offlinerl"},{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114,"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":"2107.06106","title":"Conservative Offline Distributional Reinforcement Learning","created":"2021-07-12","cited_by_count":79,"area":"offlinerl"},{"id":"2107.11003","title":"Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings","created":"2021-07-23","cited_by_count":68,"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":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"area":null},{"id":"2307.07055","title":"Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement","created":"2023-07-13","cited_by_count":49,"area":"diffusion"},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2203.06662","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","created":"2022-03-13","cited_by_count":41,"area":"offlinerl"},{"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":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36,"area":null},{"id":"2111.06784","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes","created":"2021-11-12","cited_by_count":36,"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":"2203.13935","title":"Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps","created":"2022-03-25","cited_by_count":34,"area":"offlinerl"},{"id":"2305.08062","title":"Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling","created":"2023-05-14","cited_by_count":34,"area":null},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"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":"2110.14000","title":"Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning","created":"2021-10-26","cited_by_count":32,"area":"offlinerl"},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32,"area":null},{"id":"2101.02808","title":"Average-Reward Off-Policy Policy Evaluation with Function Approximation","created":"2021-01-08","cited_by_count":31,"area":null},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31,"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":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"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":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"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":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","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":"2306.03552","title":"State Regularized Policy Optimization on Data with Dynamics Shift","created":"2023-06-06","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":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22,"area":null},{"id":"2206.02371","title":"Markovian Interference in Experiments","created":"2022-06-06","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":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21,"area":null},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2103.02827","title":"On the Convergence and Optimality of Policy Gradient for Markov Coherent Risk","created":"2021-03-04","cited_by_count":20,"area":null},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2302.02252","title":"Reinforcement Learning in Low-Rank MDPs with Density Features","created":"2023-02-04","cited_by_count":18,"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":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","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":"2103.02084","title":"Minimax Model Learning","created":"2021-03-02","cited_by_count":16,"area":null},{"id":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16,"area":"offlinerl"},{"id":"2212.13861","title":"Offline Reinforcement Learning via Linear-Programming with Error-Bound Induced Constraints","created":"2022-12-28","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":"2206.06711","title":"Conformal Off-policy Prediction","created":"2022-06-14","cited_by_count":14,"area":null},{"id":"2206.07166","title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning","created":"2022-06-14","cited_by_count":14,"area":"offlinerl"},{"id":"2210.05922","title":"A Unified Framework for Alternating Offline Model Training and Policy Learning","created":"2022-10-12","cited_by_count":14,"area":"offlinerl"},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","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":"2106.11519","title":"Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2302.00662","title":"Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders","created":"2023-02-01","cited_by_count":13,"area":"offlinerl"},{"id":"2311.18207","title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2402.06151","title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition","created":"2024-02-09","cited_by_count":13,"area":"deeprl"},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2204.00956","title":"Model-Free and Model-Based Policy Evaluation when Causality is Uncertain","created":"2022-04-02","cited_by_count":12,"area":null},{"id":"2206.04890","title":"Adversarial Counterfactual Environment Model Learning","created":"2022-06-10","cited_by_count":12,"area":null},{"id":"2305.00303","title":"A Coupled Flow Approach to Imitation Learning","created":"2023-04-29","cited_by_count":12,"area":"offlinerl"},{"id":"2305.02542","title":"Correcting for Interference in Experiments: A Case Study at Douyin","created":"2023-05-04","cited_by_count":12,"area":null},{"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":"2510.22512","title":"Transitive RL: Value Learning via Divide and Conquer","created":"2025-10-26","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":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2602.17616","title":"Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs","created":"2026-02-19","cited_by_count":11,"area":null},{"id":"2108.05338","title":"Truncated Emphatic Temporal Difference Methods for Prediction and Control","created":"2021-08-11","cited_by_count":10,"area":null},{"id":"2201.12594","title":"Robust Imitation Learning from Corrupted Demonstrations","created":"2022-01-29","cited_by_count":10,"area":"offlinerl"},{"id":"2202.13163","title":"Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons","created":"2022-02-26","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":"2405.21043","title":"Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation","created":"2024-05-31","cited_by_count":10,"area":null},{"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":"2603.06743","title":"Stabilizing Reinforcement Learning for Diffusion Language Models","created":"2026-03-06","cited_by_count":10,"area":"lr"},{"id":"2110.12468","title":"False Correlation Reduction for Offline Reinforcement Learning","created":"2021-10-24","cited_by_count":9,"area":"offlinerl"},{"id":"2202.11133","title":"Continual Auxiliary Task Learning","created":"2022-02-22","cited_by_count":9,"area":null},{"id":"2306.13284","title":"Correcting discount-factor mismatch in on-policy policy gradient methods","created":"2023-06-23","cited_by_count":9,"area":null},{"id":"2312.01457","title":"Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits","created":"2023-12-03","cited_by_count":9,"area":null},{"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":"2101.09847","title":"High-Confidence Off-Policy (or Counterfactual) Variance Estimation","created":"2021-01-25","cited_by_count":8,"area":null},{"id":"2202.10887","title":"Policy Evaluation for Temporal and/or Spatial Dependent Experiments","created":"2022-02-22","cited_by_count":8,"area":null},{"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":"2302.02477","title":"Offline Learning of Closed-Loop Deep Brain Stimulation Controllers for Parkinson Disease Treatment","created":"2023-02-05","cited_by_count":8,"area":null},{"id":"2402.08201","title":"Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap","created":"2024-02-13","cited_by_count":8,"area":"deeprl"},{"id":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2503.01134","title":"Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs","created":"2025-03-03","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":"2212.07486","title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","created":"2022-12-14","cited_by_count":7,"area":null}],"next_cursor":"100"}