{"total":56,"rows":[{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87,"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":"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":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","cited_by_count":21,"area":null},{"id":"2206.02626","title":"Infinite Recommendation Networks: A Data-Centric Approach","created":"2022-06-03","cited_by_count":20,"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":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15,"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":"2307.15053","title":"On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation","created":"2023-07-27","cited_by_count":13,"area":null},{"id":"2212.11431","title":"Local Policy Improvement for Recommender Systems","created":"2022-12-22","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":"2201.04768","title":"On Sampling Collaborative Filtering Datasets","created":"2022-01-13","cited_by_count":8,"area":null},{"id":"2208.06263","title":"Probabilistic Rank and Reward: A Scalable Model for Slate Recommendation","created":"2022-08-10","cited_by_count":8,"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":"2107.11533","title":"Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support","created":"2021-07-24","cited_by_count":7,"area":null},{"id":"2302.02944","title":"Learning Complementary Policies for Human-AI Teams","created":"2023-02-06","cited_by_count":7,"area":null},{"id":"2305.03954","title":"Learning Action Embeddings for Off-Policy Evaluation","created":"2023-05-06","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":"2111.09933","title":"Loss Functions for Discrete Contextual Pricing with Observational Data","created":"2021-11-18","cited_by_count":6,"area":null},{"id":"2202.01721","title":"Variance-Optimal Augmentation Logging for Counterfactual Evaluation in Contextual Bandits","created":"2022-02-03","cited_by_count":6,"area":null},{"id":"2302.12120","title":"Sequential Counterfactual Risk Minimization","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2112.04461","title":"Enhancing Counterfactual Classification via Self-Training","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2302.12736","title":"Balanced Off-Policy Evaluation for Personalized Pricing","created":"2023-02-24","cited_by_count":5,"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":"2204.07135","title":"Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2212.01925","title":"Counterfactual Learning with General Data-generating Policies","created":"2022-12-04","cited_by_count":3,"area":null},{"id":"2307.07014","title":"Leveraging Factored Action Spaces for Off-Policy Evaluation","created":"2023-07-13","cited_by_count":3,"area":null},{"id":"2609.22819","title":"Counterfactual Tool Ranking under Utility, Cost, and Privilege Constraints","created":"2026-09-19","cited_by_count":3,"area":null},{"id":"2502.21304","title":"Clustering Context in Off-Policy Evaluation","created":"2025-02-28","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":"2111.08587","title":"Offline Contextual Bandits for Wireless Network Optimization","created":"2021-11-11","cited_by_count":1,"area":null},{"id":"2202.10944","title":"Convex Surrogate Loss Functions for Contextual Pricing with Transaction Data","created":"2022-02-16","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":"2504.17277","title":"ExOSITO: Explainable Off-Policy Learning with Side Information for Intensive Care Unit Blood Test Orders","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2506.14439","title":"A General Framework for Off-Policy Learning with Partially-Observed Reward","created":"2025-06-17","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":"2607.01958","title":"A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods","created":"2026-07-02","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":"2206.03851","title":"Reconsidering Learning Objectives in Unbiased Recommendation with Unobserved Confounders","created":"2022-06-07","cited_by_count":0,"area":null},{"id":"2208.14980","title":"Inverse Propensity Score based offline estimator for deterministic ranking lists using position bias","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2302.13505","title":"Multi-Action Dialog Policy Learning from Logged User Feedback","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2310.12026","title":"Nonparametric Discrete Choice Experiments with Machine Learning Guided Adaptive Design","created":"2023-10-18","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":"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":"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":"2603.22900","title":"Off-Policy Evaluation and Learning for Survival Outcomes under Censoring","created":"2026-03-24","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":"2606.07399","title":"Are Good Generators Good Decision-Makers? Policy Learning for General Interventions via Retargeted Counterfactual Generation","created":"2026-06-05","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":"2608.22221","title":"Counterfactual Evaluation of Temporal Observation Protocols","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.08725","title":"BAFF: Bid-Aware Filter Family for Mitigating Training Data Interference in RTB A/B Tests","created":"2026-09-08","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},{"id":"2610.16280","title":"agent-risk: Risk Assessment for Changes to AI Agents","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}