{"total":23,"rows":[{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2102.05829","title":"Causal Inference for Time series Analysis: Problems, Methods and Evaluation","created":"2021-02-11","cited_by_count":42,"area":null},{"id":"2206.03944","title":"Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines","created":"2022-06-08","cited_by_count":22,"area":null},{"id":"2211.14297","title":"Doubly robust nearest neighbors in factor models","created":"2022-11-25","cited_by_count":9,"area":null},{"id":"2202.10887","title":"Policy Evaluation for Temporal and/or Spatial Dependent Experiments","created":"2022-02-22","cited_by_count":8,"area":null},{"id":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"area":null},{"id":"2304.05365","title":"Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2403.17285","title":"Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments","created":"2024-03-26","cited_by_count":6,"area":null},{"id":"2102.00102","title":"Adaptive Sequential Design for a Single Time-Series","created":"2021-01-29","cited_by_count":4,"area":null},{"id":"2202.10574","title":"A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets","created":"2022-02-21","cited_by_count":4,"area":null},{"id":"2306.14672","title":"PWSHAP: A Path-Wise Explanation Model for Targeted Variables","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2501.06534","title":"Dynamic Causal Structure Discovery and Causal Effect Estimation","created":"2025-01-11","cited_by_count":3,"area":null},{"id":"2311.14359","title":"Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2505.16311","title":"Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2511.02944","title":"Power Constrained Nonstationary Bandits with Habituation and Recovery Dynamics","created":"2025-11-04","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":"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":"2306.16297","title":"A Meta-Learning Method for Estimation of Causal Excursion Effects to Assess Time-Varying Moderation","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2402.01995","title":"Online Uniform Sampling: Randomized Learning-Augmented Approximation Algorithms with Application to Digital Health","created":"2024-02-03","cited_by_count":0,"area":null},{"id":"2512.08828","title":"Prediction Intervals for Individual Treatment Effects in a Multiple Decision Point Framework using Conformal Inference","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2605.30319","title":"Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.17772","title":"When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.38695","title":"Always-On Experimentation","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}