{"total":27,"rows":[{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"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":"2103.08390","title":"Estimating the Long-Term Effects of Novel Treatments","created":"2021-03-15","cited_by_count":8,"area":null},{"id":"2306.05637","title":"On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2310.08672","title":"Machine Learning Who to Nudge: Causal vs Predictive Targeting in a Field Experiment on Student Financial Aid Renewal","created":"2023-10-12","cited_by_count":8,"area":null},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2112.04571","title":"Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2302.09212","title":"HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare","created":"2023-02-18","cited_by_count":5,"area":null},{"id":"2201.12692","title":"Meta-Learners for Estimation of Causal Effects: Finite Sample Cross-Fit Performance","created":"2022-01-30","cited_by_count":4,"area":null},{"id":"2204.07124","title":"Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2302.08551","title":"Infinite Action Contextual Bandits with Reusable Data Exhaust","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2104.10554","title":"Calibrated Optimal Decision Making with Multiple Data Sources and Limited Outcome","created":"2021-04-21","cited_by_count":1,"area":null},{"id":"2104.10573","title":"GEAR: On Optimal Decision Making with Auxiliary Data","created":"2021-04-21","cited_by_count":1,"area":null},{"id":"2206.10261","title":"Interpretable Deep Causal Learning for Moderation Effects","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2211.11119","title":"Counterfactual Learning with Multioutput Deep Kernels","created":"2022-11-20","cited_by_count":1,"area":null},{"id":"2306.09800","title":"$\\pi2\\text{vec}$: Policy Representations with Successor Features","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2309.13365","title":"Limits of Actor-Critic Algorithms for Decision Tree Policies Learning in IBMDPs","created":"2023-09-23","cited_by_count":1,"area":null},{"id":"2103.01280","title":"Dynamic covariate balancing: estimating treatment effects over time with potential local projections","created":"2021-03-01","cited_by_count":0,"area":null},{"id":"2106.05031","title":"Estimation of Optimal Dynamic Treatment Assignment Rules under Policy Constraints","created":"2021-06-09","cited_by_count":0,"area":null},{"id":"2208.09551","title":"Game-Theoretic Algorithms for Conditional Moment Matching","created":"2022-08-19","cited_by_count":0,"area":null},{"id":"2301.00927","title":"Deep Spectral Q-learning with Application to Mobile Health","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2301.12553","title":"Asymptotic Inference for Multi-Stage Stationary Treatment Policy with Variable Selection","created":"2023-01-29","cited_by_count":0,"area":null},{"id":"2310.09545","title":"A Semiparametric Instrumented Difference-in-Differences Approach to Policy Learning","created":"2023-10-14","cited_by_count":0,"area":null},{"id":"2407.16062","title":"Artificial Intelligence-based Decision Support Systems for Precision and Digital Health","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2503.15890","title":"Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2507.20993","title":"Annotation-Assisted Learning of Treatment Policies From Multimodal Electronic Health Records","created":"2025-07-28","cited_by_count":0,"area":null}],"next_cursor":null}