{"total":30,"rows":[{"id":"2103.15209","title":"Understanding the role of importance weighting for deep learning","created":"2021-03-28","cited_by_count":39,"area":null},{"id":"2202.09667","title":"Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning","created":"2022-02-19","cited_by_count":34,"area":null},{"id":"2110.12343","title":"Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability","created":"2021-10-24","cited_by_count":24,"area":null},{"id":"2303.01049","title":"Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2102.11724","title":"Causal Mediation Analysis with Hidden Confounders","created":"2021-02-21","cited_by_count":10,"area":null},{"id":"2212.11431","title":"Local Policy Improvement for Recommender Systems","created":"2022-12-22","cited_by_count":9,"area":null},{"id":"2202.03888","title":"Learning MAX-SAT from Contextual Examples for Combinatorial Optimisation","created":"2022-02-08","cited_by_count":8,"area":null},{"id":"2106.04443","title":"Robust Generalization despite Distribution Shift via Minimum Discriminating Information","created":"2021-06-08","cited_by_count":6,"area":null},{"id":"2105.10590","title":"Parallelizing Contextual Bandits","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2207.03618","title":"PoseGU: 3D Human Pose Estimation with Novel Human Pose Generator and Unbiased Learning","created":"2022-07-07","cited_by_count":4,"area":null},{"id":"2106.03934","title":"Offline Policy Comparison under Limited Historical Agent-Environment Interactions","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2106.12886","title":"Constrained Classification and Policy Learning","created":"2021-06-24","cited_by_count":3,"area":null},{"id":"2111.03267","title":"Interpretable Personalized Experimentation","created":"2021-11-05","cited_by_count":3,"area":null},{"id":"2202.06657","title":"The Impact of Batch Learning in Stochastic Linear Bandits","created":"2022-02-14","cited_by_count":3,"area":null},{"id":"2109.04746","title":"Counterfactual Adversarial Learning with Representation Interpolation","created":"2021-09-10","cited_by_count":2,"area":null},{"id":"2206.12701","title":"The Bandwagon Effect: Not Just Another Bias","created":"2022-06-25","cited_by_count":2,"area":null},{"id":"2302.00370","title":"How to select predictive models for causal inference?","created":"2023-02-01","cited_by_count":2,"area":null},{"id":"2401.03756","title":"Adaptive Experimental Design for Policy Learning","created":"2024-01-08","cited_by_count":2,"area":null},{"id":"2111.11113","title":"Case-based off-policy policy evaluation using prototype learning","created":"2021-11-22","cited_by_count":1,"area":null},{"id":"2202.13337","title":"Towards Robust Off-policy Learning for Runtime Uncertainty","created":"2022-02-27","cited_by_count":1,"area":null},{"id":"2210.10631","title":"Simulated Contextual Bandits for Personalization Tasks from Recommendation Datasets","created":"2022-10-12","cited_by_count":1,"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":"2502.11953","title":"Refined PAC-Bayes Bounds for Offline Bandits","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2108.00151","title":"An Empirical Analysis on Transparent Algorithmic Exploration in Recommender Systems","created":"2021-07-31","cited_by_count":0,"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":"2310.05324","title":"Increasing Entropy to Boost Policy Gradient Performance on Personalization Tasks","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2502.08993","title":"Off-Policy Evaluation for Recommendations with Missing-Not-At-Random Rewards","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2503.23630","title":"Finding Interest Needle in Popularity Haystack: Improving Retrieval by Modeling Item Exposure","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2606.00700","title":"COPF: An Online Framework for Deployment-Stable Counterfactual Fairness in Evolving Graphs","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2609.29007","title":"When Does Action Credit Need Updating?","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}