{"total":29,"rows":[{"id":"2301.09937","title":"Explainable Deep Reinforcement Learning: State of the Art and Challenges","created":"2023-01-24","cited_by_count":33,"area":null},{"id":"2202.08434","title":"A Survey of Explainable Reinforcement Learning","created":"2022-02-17","cited_by_count":31,"area":null},{"id":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"id":"2203.06369","title":"The Health Gym: Synthetic Health-Related Datasets for the Development of Reinforcement Learning Algorithms","created":"2022-03-12","cited_by_count":19,"area":null},{"id":"2106.12729","title":"Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators","created":"2021-06-24","cited_by_count":17,"area":null},{"id":"2206.02887","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2208.08655","title":"Generating Synthetic Clinical Data that Capture Class Imbalanced Distributions with Generative Adversarial Networks: Example using Antiretroviral Therapy for HIV","created":"2022-08-18","cited_by_count":12,"area":null},{"id":"2106.04240","title":"The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation","created":"2021-06-08","cited_by_count":11,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2112.03914","title":"Synthetic Acute Hypotension and Sepsis Datasets Based on MIMIC-III and Published as Part of the Health Gym Project","created":"2021-12-07","cited_by_count":5,"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":"2201.08262","title":"Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making","created":"2022-01-20","cited_by_count":4,"area":null},{"id":"2109.06310","title":"State Relevance for Off-Policy Evaluation","created":"2021-09-13","cited_by_count":3,"area":null},{"id":"2306.11208","title":"The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2210.13958","title":"Mitigating Health Data Poverty: Generative Approaches versus Resampling for Time-series Clinical Data","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2211.16566","title":"Relative Sparsity for Medical Decision Problems","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2407.19380","title":"Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment","created":"2024-07-28","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":"2411.07372","title":"Identifying Differential Patient Care Through Inverse Intent Inference","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2411.19395","title":"Concept-driven Off Policy Evaluation","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2510.22878","title":"Limits of Generative Pre-Training in Structured EMR Trajectories with Irregular Sampling","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2301.09941","title":"ASQ-IT: Interactive Explanations for Reinforcement-Learning Agents","created":"2023-01-24","cited_by_count":0,"area":null},{"id":"2306.14297","title":"Inference for relative sparsity","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2307.01519","title":"Deep Attention Q-Network for Personalized Treatment Recommendation","created":"2023-07-04","cited_by_count":0,"area":null},{"id":"2406.11850","title":"Closed-loop Teaching via Demonstrations to Improve Policy Transparency","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2505.13324","title":"From What Ifs to Insights: Counterfactuals in Causal Inference vs. Explainable AI","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2506.23040","title":"Treatment, evidence, imitation, and chat","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2602.10643","title":"Evaluation metrics for temporal preservation in synthetic longitudinal patient data","created":"2026-02-11","cited_by_count":0,"area":null}],"next_cursor":null}