{"total":73,"rows":[{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"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":"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":"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":"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":"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":"2201.03522","title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","created":"2022-01-10","cited_by_count":28,"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":"2112.03097","title":"Flexible Option Learning","created":"2021-12-06","cited_by_count":25,"area":null},{"id":"2206.04405","title":"Conformal Off-Policy Prediction in Contextual Bandits","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2109.12002","title":"Optimal policy evaluation using kernel-based temporal difference methods","created":"2021-09-24","cited_by_count":24,"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":"2109.14180","title":"Efficient Reinforced Feature Selection via Early Stopping Traverse Strategy","created":"2021-09-29","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":"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":"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":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","cited_by_count":16,"area":null},{"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":"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":"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":"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":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","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":"2101.09847","title":"High-Confidence Off-Policy (or Counterfactual) Variance Estimation","created":"2021-01-25","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":"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},{"id":"2310.17146","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2202.11079","title":"Reward-Free Policy Space Compression for Reinforcement Learning","created":"2022-02-22","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":"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":"2406.01389","title":"RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"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":"2212.03932","title":"Low Variance Off-policy Evaluation with State-based Importance Sampling","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2302.09212","title":"HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare","created":"2023-02-18","cited_by_count":5,"area":null},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2106.03934","title":"Offline Policy Comparison under Limited Historical Agent-Environment Interactions","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2109.06310","title":"State Relevance for Off-Policy Evaluation","created":"2021-09-13","cited_by_count":3,"area":null},{"id":"2312.11551","title":"Probabilistic Offline Policy Ranking with Approximate Bayesian Computation","created":"2023-12-17","cited_by_count":3,"area":null},{"id":"2505.00304","title":"Reinforcement Learning with Continuous Actions Under Unmeasured Confounding","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2106.10566","title":"Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling","created":"2021-06-19","cited_by_count":2,"area":null},{"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":"2209.07074","title":"On the Reuse Bias in Off-Policy Reinforcement Learning","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2301.10330","title":"Off-Policy Evaluation for Action-Dependent Non-Stationary Environments","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2301.13348","title":"A Reinforcement Learning Framework for Dynamic Mediation Analysis","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2307.15892","title":"A new Gradient TD Algorithm with only One Step-size: Convergence Rate Analysis using $L$-$\\lambda$ Smoothness","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2404.00195","title":"Multiple-policy Evaluation via Density Estimation","created":"2024-03-29","cited_by_count":2,"area":null},{"id":"2507.06961","title":"Off-Policy Evaluation Under Nonignorable Missing Data","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2109.06625","title":"Towards optimized actions in critical situations of soccer games with deep reinforcement learning","created":"2021-09-14","cited_by_count":1,"area":null},{"id":"2202.00076","title":"Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2202.13337","title":"Towards Robust Off-policy Learning for Runtime Uncertainty","created":"2022-02-27","cited_by_count":1,"area":null},{"id":"2411.19395","title":"Concept-driven Off Policy Evaluation","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2501.02353","title":"Reweighting Improves Conditional Risk Bounds","created":"2025-01-04","cited_by_count":1,"area":null},{"id":"2505.17506","title":"Offline Constrained Reinforcement Learning under Partial Data Coverage","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2605.29500","title":"Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2203.16177","title":"Marginalized Operators for Off-policy Reinforcement Learning","created":"2022-03-30","cited_by_count":0,"area":null},{"id":"2301.03183","title":"Minimax Weight Learning for Absorbing MDPs","created":"2023-01-09","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":"2505.00961","title":"DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects","created":"2025-05-02","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":"2605.06474","title":"Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.14284","title":"Smooth Multi-Policy Causal Effect Estimation in Longitudinal Settings","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.25923","title":"$\\text{DT}^2$: Decision-Targeted Digital Twins","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.20389","title":"Model-based Bootstrap for Offline Policy Evaluation in Tabular Reinforcement Learning","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.39634","title":"Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive Reuse","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}