{"total":119,"rows":[{"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":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2506.00613","title":"WorldGym: World Model as An Environment for Policy Evaluation","created":"2025-05-31","cited_by_count":64,"area":"wm"},{"id":"2210.00035","title":"Neural Causal Models for Counterfactual Identification and Estimation","created":"2022-09-30","cited_by_count":57,"area":null},{"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":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2103.13883","title":"Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning","created":"2021-03-25","cited_by_count":42,"area":"offlinerl"},{"id":"2110.15332","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","created":"2021-10-28","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":"2104.14074","title":"Statistical Inference with M-Estimators on Adaptively Collected Data","created":"2021-04-29","cited_by_count":40,"area":null},{"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":"2202.09667","title":"Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning","created":"2022-02-19","cited_by_count":34,"area":null},{"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":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"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":"2011.04019","title":"Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient","created":"2020-11-08","cited_by_count":24,"area":"offlinerl"},{"id":"2109.12002","title":"Optimal policy evaluation using kernel-based temporal difference methods","created":"2021-09-24","cited_by_count":24,"area":null},{"id":"2110.12343","title":"Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability","created":"2021-10-24","cited_by_count":24,"area":null},{"id":"2104.03220","title":"DoubleML -- An Object-Oriented Implementation of Double Machine Learning in Python","created":"2021-04-07","cited_by_count":23,"area":null},{"id":"2206.02371","title":"Markovian Interference in Experiments","created":"2022-06-06","cited_by_count":22,"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":"2407.05287","title":"Model-agnostic meta-learners for estimating heterogeneous treatment effects over time","created":"2024-07-07","cited_by_count":19,"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":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16,"area":"offlinerl"},{"id":"2302.04334","title":"Asking for Help: Failure Prediction in Behavioral Cloning through Value Approximation","created":"2023-02-08","cited_by_count":16,"area":"offlinerl"},{"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":"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":"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":"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":"2303.01076","title":"Hallucinated Adversarial Control for Conservative Offline Policy Evaluation","created":"2023-03-02","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":"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":"2206.02887","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":"2210.00750","title":"Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient","created":"2022-10-03","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":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"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":"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":"2405.21012","title":"IGC-Net for conditional average potential outcome estimation over time","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2211.14297","title":"Doubly robust nearest neighbors in factor models","created":"2022-11-25","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":"2312.01530","title":"Evaluation of Active Feature Acquisition Methods for Time-varying Feature Settings","created":"2023-12-03","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":"2103.08390","title":"Estimating the Long-Term Effects of Novel Treatments","created":"2021-03-15","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":"2207.04771","title":"Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions","created":"2022-07-11","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":"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":"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":"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":"2505.13092","title":"Treatment Effect Estimation for Optimal Decision-Making","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2207.00632","title":"Offline Policy Optimization with Eligible Actions","created":"2022-07-01","cited_by_count":7,"area":"offlinerl"},{"id":"2306.08719","title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2106.04443","title":"Robust Generalization despite Distribution Shift via Minimum Discriminating Information","created":"2021-06-08","cited_by_count":6,"area":null},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2112.04571","title":"Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2301.06240","title":"Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency","created":"2023-01-16","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":"2310.16638","title":"Double Debiased Covariate Shift Adaptation Robust to Density-Ratio Estimation","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2311.18206","title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","created":"2023-11-30","cited_by_count":6,"area":"offlinerl"},{"id":"2403.17285","title":"Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments","created":"2024-03-26","cited_by_count":6,"area":null},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2101.04025","title":"Distributed Double Machine Learning with a Serverless Architecture","created":"2021-01-11","cited_by_count":5,"area":null},{"id":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2111.14272","title":"Identification of Subgroups With Similar Benefits in Off-Policy Policy Evaluation","created":"2021-11-28","cited_by_count":5,"area":null},{"id":"2212.14466","title":"Quantile Off-Policy Evaluation via Deep Conditional Generative Learning","created":"2022-12-29","cited_by_count":5,"area":null},{"id":"2301.11426","title":"Model-based Offline Reinforcement Learning with Local Misspecification","created":"2023-01-26","cited_by_count":5,"area":"offlinerl"},{"id":"2206.00885","title":"Coordinated Double Machine Learning","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2312.03619","title":"Evaluation of Active Feature Acquisition Methods for Static Feature Settings","created":"2023-12-06","cited_by_count":4,"area":"offlinerl"},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2410.17538","title":"Primal-Dual Spectral Representation for Off-policy Evaluation","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"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":"2404.00099","title":"Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes","created":"2024-03-29","cited_by_count":3,"area":null},{"id":"2409.02747","title":"Tractable Offline Learning of Regular Decision Processes","created":"2024-09-04","cited_by_count":3,"area":"offlinerl"},{"id":"2512.11150","title":"Causal Judge Evaluation: Calibrated Surrogate Metrics for LLM Systems","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2512.23694","title":"Bellman Calibration for $V$-Learning in Offline Reinforcement Learning","created":"2025-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2203.12048","title":"Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning","created":"2022-03-22","cited_by_count":2,"area":null},{"id":"2408.12004","title":"CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2502.16195","title":"Statistical Inference in Reinforcement Learning: A Selective Survey","created":"2025-02-22","cited_by_count":2,"area":"deeprl"},{"id":"2506.10677","title":"Exploiting Similarities in A/B Testing with Off-Policy Estimation","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2507.18118","title":"A Two-armed Bandit Framework for A/B Testing","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2510.26026","title":"Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation","created":"2025-10-29","cited_by_count":2,"area":"deeprl"},{"id":"2512.23805","title":"Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2208.13701","title":"Data-Driven Influence Functions for Optimization-Based Causal Inference","created":"2022-08-29","cited_by_count":1,"area":null},{"id":"2501.00854","title":"A Graphical Approach to State Variable Selection in Off-policy Learning","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2505.22492","title":"Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation","created":"2025-05-28","cited_by_count":1,"area":"deeprl"},{"id":"2602.01853","title":"Designing Time Series Experiments in A/B Testing with Transformer Reinforcement Learning","created":"2026-02-02","cited_by_count":1,"area":"deeprl"},{"id":"2603.28681","title":"Functional Natural Policy Gradients","created":"2026-03-30","cited_by_count":1,"area":"deeprl"},{"id":"2209.05186","title":"Statistical Estimation of Confounded Linear MDPs: An Instrumental Variable Approach","created":"2022-09-12","cited_by_count":0,"area":null},{"id":"2301.12553","title":"Asymptotic Inference for Multi-Stage Stationary Treatment Policy with Variable Selection","created":"2023-01-29","cited_by_count":0,"area":null}],"next_cursor":"100"}