{"total":22,"rows":[{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"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":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2403.02467","title":"Applied Causal Inference Powered by ML and AI","created":"2024-03-04","cited_by_count":30,"area":null},{"id":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","cited_by_count":21,"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":"2210.15345","title":"PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits","created":"2022-10-25","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":"2305.19742","title":"Reliable Off-Policy Learning for Dosage Combinations","created":"2023-05-31","cited_by_count":15,"area":null},{"id":"2407.07596","title":"Learning treatment effects while treating those in need","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2302.12120","title":"Sequential Counterfactual Risk Minimization","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2311.02467","title":"Individualized Policy Evaluation and Learning under Clustered Network Interference","created":"2023-11-04","cited_by_count":6,"area":null},{"id":"2301.05491","title":"Efficient and robust transfer learning of optimal individualized treatment regimes with right-censored survival data","created":"2023-01-13","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":"2602.09456","title":"Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2301.11461","title":"Learning to Generate All Feasible Actions","created":"2023-01-26","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":"2309.07176","title":"Mind the Gap: Optimal and Equitable Encouragement Policies","created":"2023-09-12","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":"2510.15483","title":"Fast Best-in-Class Regret for Contextual Bandits","created":"2025-10-17","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}],"next_cursor":null}