{"total":23,"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":"2106.00418","title":"Post-Contextual-Bandit Inference","created":"2021-06-01","cited_by_count":32,"area":null},{"id":"2108.13703","title":"Evaluating the Robustness of Off-Policy Evaluation","created":"2021-08-31","cited_by_count":32,"area":null},{"id":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"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":"2102.09540","title":"Off-policy Confidence Sequences","created":"2021-02-18","cited_by_count":15,"area":null},{"id":"2106.07914","title":"Control Variates for Slate Off-Policy Evaluation","created":"2021-06-15","cited_by_count":13,"area":null},{"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":"2106.01723","title":"Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning","created":"2021-06-03","cited_by_count":10,"area":null},{"id":"2209.08860","title":"A Survey of Deep Causal Models and Their Industrial Applications","created":"2022-09-19","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":"2505.13092","title":"Treatment Effect Estimation for Optimal Decision-Making","created":"2025-05-19","cited_by_count":8,"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":"2602.08892","title":"Winner's Curse Drives False Promises in Data-Driven Decisions: A Case Study in Refugee Matching","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2308.14165","title":"Distributional Off-Policy Evaluation for Slate Recommendations","created":"2023-08-27","cited_by_count":2,"area":null},{"id":"2406.18022","title":"Automated Off-Policy Estimator Selection via Supervised Learning","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2502.21304","title":"Clustering Context in Off-Policy Evaluation","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2602.10608","title":"Bayesian Inference of Contextual Bandit Policies via Empirical Likelihood","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2302.11725","title":"Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments","created":"2023-02-23","cited_by_count":1,"area":null},{"id":"2102.08975","title":"Adaptive Doubly Robust Estimator from Non-stationary Logging Policy under a Convergence of Average Probability","created":"2021-02-17","cited_by_count":0,"area":null},{"id":"2207.01722","title":"A Causal Approach for Business Optimization: Application on an Online Marketplace","created":"2022-07-04","cited_by_count":0,"area":null},{"id":"2408.13484","title":"IntOPE: Off-Policy Evaluation in the Presence of Interference","created":"2024-08-24","cited_by_count":0,"area":null},{"id":"2607.15067","title":"Kernel weighted importance sampling for off-policy evaluation in contextual bandits","created":"2026-07-16","cited_by_count":0,"area":null}],"next_cursor":null}