{"total":26,"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":"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":"2112.03097","title":"Flexible Option Learning","created":"2021-12-06","cited_by_count":25,"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":"2110.15590","title":"Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoff","created":"2021-10-29","cited_by_count":13,"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":"2602.17616","title":"Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs","created":"2026-02-19","cited_by_count":11,"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":"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":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2111.08172","title":"Off-Policy Actor-Critic with Emphatic Weightings","created":"2021-11-16","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":"2306.15625","title":"Value-aware Importance Weighting for Off-policy Reinforcement Learning","created":"2023-06-27","cited_by_count":4,"area":null},{"id":"2307.11897","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","created":"2023-07-21","cited_by_count":4,"area":null},{"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":"2203.10172","title":"Importance Sampling Placement in Off-Policy Temporal-Difference Methods","created":"2022-03-18","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":"2605.11519","title":"Controllable User Simulation","created":"2026-05-12","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":"2312.15458","title":"Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation","created":"2023-12-24","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":"2610.14440","title":"Target-ESS Tempered Policy Optimization (TETPO): Smooth Variance Control via Bridge Importance Sampling","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}