{"total":58,"rows":[{"id":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"area":null},{"id":"2104.02929","title":"Minimax Kernel Machine Learning for a Class of Doubly Robust Functionals with Application to Proximal Causal Inference","created":"2021-04-07","cited_by_count":20,"area":null},{"id":"2210.13132","title":"PAC-Bayesian Offline Contextual Bandits With Guarantees","created":"2022-10-24","cited_by_count":20,"area":null},{"id":"2106.00808","title":"Invariant Policy Learning: A Causal Perspective","created":"2021-06-01","cited_by_count":17,"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":"2306.07923","title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","created":"2023-06-13","cited_by_count":15,"area":"offlinerl"},{"id":"2206.06711","title":"Conformal Off-policy Prediction","created":"2022-06-14","cited_by_count":14,"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":"2405.18902","title":"A Causal Framework for Evaluating Deferring Systems","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"id":"2303.08516","title":"Fair Off-Policy Learning from Observational Data","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2202.13163","title":"Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons","created":"2022-02-26","cited_by_count":10,"area":"offlinerl"},{"id":"2405.02141","title":"Multi-Objective Recommendation via Multivariate Policy Learning","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2309.04470","title":"On the Actionability of Outcome Prediction","created":"2023-09-08","cited_by_count":9,"area":null},{"id":"2405.20487","title":"Probabilities of Causation for Continuous and Vector Variables","created":"2024-05-30","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":"2504.19342","title":"Contextual Online Uncertainty-Aware Preference Learning for Human Feedback","created":"2025-04-27","cited_by_count":7,"area":"alignment"},{"id":"2210.13373","title":"Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions","created":"2022-10-24","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":"2311.18206","title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","created":"2023-11-30","cited_by_count":6,"area":"offlinerl"},{"id":"2502.13022","title":"Efficient and Sharp Off-Policy Learning under Unobserved Confounding","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2302.12736","title":"Balanced Off-Policy Evaluation for Personalized Pricing","created":"2023-02-24","cited_by_count":5,"area":null},{"id":"2104.10334","title":"Automatic Double Machine Learning for Continuous Treatment Effects","created":"2021-04-21","cited_by_count":4,"area":null},{"id":"2105.09254","title":"Multiply Robust Causal Mediation Analysis with Continuous Treatments","created":"2021-05-19","cited_by_count":4,"area":null},{"id":"2110.15501","title":"Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning","created":"2021-10-29","cited_by_count":4,"area":null},{"id":"2309.12819","title":"Doubly Robust Proximal Causal Learning for Continuous Treatments","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2605.15133","title":"Causal Foundation Models with Continuous Treatments","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2111.03267","title":"Interpretable Personalized Experimentation","created":"2021-11-05","cited_by_count":3,"area":null},{"id":"2202.12958","title":"Off-Policy Evaluation with Policy-Dependent Optimization Response","created":"2022-02-25","cited_by_count":3,"area":null},{"id":"2211.15355","title":"Causal Deep Reinforcement Learning Using Observational Data","created":"2022-11-28","cited_by_count":3,"area":null},{"id":"2301.13152","title":"STEEL: Singularity-aware Reinforcement Learning","created":"2023-01-30","cited_by_count":3,"area":"offlinerl"},{"id":"2310.06069","title":"Optimal Exploration is no harder than Thompson Sampling","created":"2023-10-09","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":"2405.18792","title":"Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies","created":"2024-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2410.08816","title":"Uncertainty-Aware Optimal Treatment Selection for Clinical Time Series","created":"2024-10-11","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":"2506.02793","title":"Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings","created":"2025-06-03","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":"2507.18118","title":"A Two-armed Bandit Framework for A/B Testing","created":"2025-07-24","cited_by_count":2,"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":"2202.12234","title":"Policy Learning for Optimal Individualized Dose Intervals","created":"2022-02-24","cited_by_count":1,"area":null},{"id":"2302.12670","title":"Personalized Pricing with Invalid Instrumental Variables: Identification, Estimation, and Policy Learning","created":"2023-02-24","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":"2208.10583","title":"Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking","created":"2022-08-22","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":"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":"2506.10664","title":"Sequential Off-Policy Learning with Logarithmic Smoothing","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2506.19049","title":"Which Company Adjustment Matter? Insights from Uplift Modeling on Financial Health","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2507.05511","title":"Deep Learning of Continuous and Structured Policies for Aggregated Heterogeneous Treatment Effects","created":"2025-07-07","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":"2604.27394","title":"Bayesian X-Learner: Calibrated Posterior Inference for Heterogeneous Treatment Effects under Heavy-Tailed Outcomes","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.16989","title":"Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection","created":"2026-05-16","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":"2606.19117","title":"Wasserstein Policy Learning for Distributional Outcomes","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.33740","title":"Weighted Spline-Expanded Networks with Distributional Balancing for Continuous Treatment Effects","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.16644","title":"Learning Deployable Causal Action Geometry under Temporal Non-Stationarity","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}