{"total":49,"rows":[{"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":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2402.02171","title":"Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction","created":"2024-02-03","cited_by_count":17,"area":null},{"id":"2306.15098","title":"Off-Policy Evaluation of Ranking Policies under Diverse User Behavior","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2405.14335","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2305.15877","title":"Exponential Smoothing for Off-Policy Learning","created":"2023-05-25","cited_by_count":15,"area":null},{"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":"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":"2302.01223","title":"Practical Bandits: An Industry Perspective","created":"2023-02-02","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":"2404.15691","title":"Long-term Off-Policy Evaluation and Learning","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2305.03954","title":"Learning Action Embeddings for Off-Policy Evaluation","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2402.14664","title":"Bayesian Off-Policy Evaluation and Learning for Large Action Spaces","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2404.15084","title":"Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2405.15332","title":"Cross-Validated Off-Policy Evaluation","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2406.06433","title":"DISCO: An End-to-End Bandit Framework for Personalised Discount Allocation","created":"2024-06-10","cited_by_count":3,"area":null},{"id":"2411.12786","title":"Off-policy estimation with adaptively collected data: the power of online learning","created":"2024-11-19","cited_by_count":3,"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":"2203.02807","title":"Off-Policy Evaluation in Embedded Spaces","created":"2022-03-05","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":"2505.08092","title":"Doubly Robust Fusion of Many Treatments for Policy Learning","created":"2025-05-12","cited_by_count":2,"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":"2507.13608","title":"Off-Policy Evaluation and Learning for Matching Markets","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2305.02914","title":"Recent Advances in the Foundations and Applications of Unbiased Learning to Rank","created":"2023-05-04","cited_by_count":1,"area":null},{"id":"2308.03443","title":"Doubly Robust Estimator for Off-Policy Evaluation with Large Action Spaces","created":"2023-08-07","cited_by_count":1,"area":null},{"id":"2404.18490","title":"Reduced-Rank Multi-objective Policy Learning and Optimization","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2504.02646","title":"Prompt Optimization with Logged Bandit Data","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2509.03456","title":"Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2603.18702","title":"Off-Policy Learning with Limited Supply","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2603.21485","title":"Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2608.28905","title":"Off-Policy Evaluation for Semantic ID Recommenders: Does the Model's Own Code Hierarchy Help?","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2309.14046","title":"Diversify and Conquer: Bandits and Diversity for an Enhanced E-commerce Homepage Experience","created":"2023-09-25","cited_by_count":0,"area":null},{"id":"2402.02152","title":"Position Paper: Why the Shooting in the Dark Method Dominates Recommender Systems Practice; A Call to Abandon Anti-Utopian Thinking","created":"2024-02-03","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":"2504.08773","title":"Counterfactual Inference under Thompson Sampling","created":"2025-04-03","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":"2506.00446","title":"Off-Policy Evaluation of Ranking Policies via Embedding-Space User Behavior Modeling","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2509.00648","title":"Context-Action Embedding Learning for Off-Policy Evaluation in Contextual Bandits","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2510.07635","title":"Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2603.09436","title":"From Weighting to Modeling: A Nonparametric Estimator for Off-Policy Evaluation","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.23022","title":"CASP: Support-Aware Offline Policy Selection for Two-Stage Recommender Systems","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.18509","title":"Offline Contextual Bandits in the Presence of New Actions","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.14604","title":"Accelerating A/B-Tests with Counterfactual Estimation: Reducing Variance through Policy Overlap","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.22012","title":"Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.28408","title":"On-Policy and Off-Policy Learning for Large Action Spaces","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.29600","title":"Adaptive Doubly Robust Off-Policy Evaluation for Ranking Policies under Diverse User Behavior","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.36740","title":"Efficient Offline Learning of Ranking Policies via Top-$k$ Policy Decomposition","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}