{"total":75,"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":"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":"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":"2102.02981","title":"Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency","created":"2021-02-05","cited_by_count":56,"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":"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":"2106.11960","title":"Variance-Aware Off-Policy Evaluation with Linear Function Approximation","created":"2021-06-22","cited_by_count":34,"area":null},{"id":"2106.00418","title":"Post-Contextual-Bandit Inference","created":"2021-06-01","cited_by_count":32,"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":"2102.00479","title":"Fast Rates for the Regret of Offline Reinforcement Learning","created":"2021-01-31","cited_by_count":26,"area":"offlinerl"},{"id":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","cited_by_count":26,"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":"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":"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":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"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":"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":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16,"area":"offlinerl"},{"id":"2310.15433","title":"Off-Policy Evaluation for Large Action Spaces via Policy Convolution","created":"2023-10-24","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":"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":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10,"area":"offlinerl"},{"id":"2209.13075","title":"Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency","created":"2022-09-26","cited_by_count":10,"area":null},{"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":"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":"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":"2505.13092","title":"Treatment Effect Estimation for Optimal Decision-Making","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2305.10187","title":"Evaluating Dynamic Conditional Quantile Treatment Effects with Applications in Ridesharing","created":"2023-05-17","cited_by_count":7,"area":null},{"id":"2306.08719","title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","created":"2023-06-14","cited_by_count":7,"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":"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":"2212.14466","title":"Quantile Off-Policy Evaluation via Deep Conditional Generative Learning","created":"2022-12-29","cited_by_count":5,"area":null},{"id":"2412.05783","title":"Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning","created":"2024-12-08","cited_by_count":5,"area":"deeprl"},{"id":"2505.20130","title":"Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2102.00102","title":"Adaptive Sequential Design for a Single Time-Series","created":"2021-01-29","cited_by_count":4,"area":null},{"id":"2202.10574","title":"A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets","created":"2022-02-21","cited_by_count":4,"area":null},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2205.15379","title":"Truly Deterministic Policy Optimization","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2211.15355","title":"Causal Deep Reinforcement Learning Using Observational Data","created":"2022-11-28","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":"2512.06244","title":"Auto-exploration for online reinforcement learning","created":"2025-12-06","cited_by_count":3,"area":"deeprl"},{"id":"2512.23694","title":"Bellman Calibration for $V$-Learning in Offline Reinforcement Learning","created":"2025-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2301.13348","title":"A Reinforcement Learning Framework for Dynamic Mediation Analysis","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2407.17910","title":"Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences","created":"2024-07-25","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":"2503.12283","title":"Towards Optimal Offline Reinforcement Learning","created":"2025-03-15","cited_by_count":2,"area":"offlinerl"},{"id":"2507.06961","title":"Off-Policy Evaluation Under Nonignorable Missing Data","created":"2025-07-09","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":"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":"2312.11863","title":"Neural Network Approximation for Pessimistic Offline Reinforcement Learning","created":"2023-12-19","cited_by_count":1,"area":"offlinerl"},{"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":"2501.02089","title":"On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures","created":"2025-01-03","cited_by_count":1,"area":"offlinerl"},{"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":"2606.05558","title":"Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents","created":"2026-06-04","cited_by_count":1,"area":"wm"},{"id":"2301.00927","title":"Deep Spectral Q-learning with Application to Mobile Health","created":"2023-01-03","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},{"id":"2504.13982","title":"When Machine Learning Meets Importance Sampling: A More Efficient Rare Event Estimation Approach","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2509.26429","title":"An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2602.01453","title":"The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2604.18972","title":"Beyond Bellman: High-Order Generator Regression for Continuous-Time Policy Evaluation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.25114","title":"Counterfactually Safe Reinforcement Learning","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2608.24858","title":"Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learning","created":"2026-08-25","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}