{"total":50,"rows":[{"id":"2202.07511","title":"Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets","created":"2022-02-15","cited_by_count":44,"area":null},{"id":"2105.01876","title":"Change Matters: Medication Change Prediction with Recurrent Residual Networks","created":"2021-05-05","cited_by_count":38,"area":null},{"id":"2202.06588","title":"Conditional Generation Net for Medication Recommendation","created":"2022-02-14","cited_by_count":30,"area":null},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2401.08957","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","created":"2024-01-17","cited_by_count":14,"area":null},{"id":"2108.04526","title":"A Survey on Deep Reinforcement Learning for Data Processing and Analytics","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2210.15598","title":"Provable Sim-to-real Transfer in Continuous Domain with Partial Observations","created":"2022-10-27","cited_by_count":9,"area":null},{"id":"2304.02169","title":"Synthesize High-dimensional Longitudinal Electronic Health Records via Hierarchical Autoregressive Language Model","created":"2023-04-04","cited_by_count":8,"area":null},{"id":"2310.16336","title":"SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process","created":"2023-10-25","cited_by_count":7,"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":"2305.12594","title":"Modeling User Satisfaction Dynamics in Dialogue via Hawkes Process","created":"2023-05-21","cited_by_count":6,"area":null},{"id":"2308.09780","title":"Event-based Dynamic Graph Representation Learning for Patent Application Trend Prediction","created":"2023-08-04","cited_by_count":6,"area":null},{"id":"2205.09852","title":"Deconfounding Actor-Critic Network with Policy Adaptation for Dynamic Treatment Regimes","created":"2022-05-19","cited_by_count":5,"area":null},{"id":"2402.04398","title":"Learning under Temporal Label Noise","created":"2024-02-06","cited_by_count":5,"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":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2410.07525","title":"Offline Inverse Constrained Reinforcement Learning for Safe-Critical Decision Making in Healthcare","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2501.07166","title":"Natural Language-Assisted Multi-modal Medication Recommendation","created":"2025-01-13","cited_by_count":4,"area":null},{"id":"2112.14479","title":"Universal Transformer Hawkes Process with Adaptive Recursive Iteration","created":"2021-12-29","cited_by_count":3,"area":null},{"id":"2507.06961","title":"Off-Policy Evaluation Under Nonignorable Missing Data","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2209.07303","title":"Differentially Private Estimation of Hawkes Process","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2210.12693","title":"Coupling User Preference with External Rewards to Enable Driver-centered and Resource-aware EV Charging Recommendation","created":"2022-10-23","cited_by_count":1,"area":null},{"id":"2212.11890","title":"Decoding surface codes with deep reinforcement learning and probabilistic policy reuse","created":"2022-12-22","cited_by_count":1,"area":null},{"id":"2212.12517","title":"NARS vs. Reinforcement learning: ONA vs. Q-Learning","created":"2022-12-23","cited_by_count":1,"area":null},{"id":"2303.08115","title":"Human-Inspired Framework to Accelerate Reinforcement Learning","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2304.12828","title":"A optimization framework for herbal prescription planning based on deep reinforcement learning","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2406.02510","title":"Fairness-Optimized Synthetic EHR Generation for Arbitrary Downstream Predictive Tasks","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2409.15377","title":"Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2506.06649","title":"SAFER: A Calibrated Risk-Aware Multimodal Recommendation Model for Dynamic Treatment Regimes","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2107.08988","title":"An Analysis of Reinforcement Learning for Malaria Control","created":"2021-07-19","cited_by_count":0,"area":null},{"id":"2108.02572","title":"SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2108.02725","title":"VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2109.05778","title":"Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2112.13058","title":"Tri-Transformer Hawkes Process: Three Heads are better than one","created":"2021-12-24","cited_by_count":0,"area":null},{"id":"2202.02830","title":"Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2203.10629","title":"Explicit User Manipulation in Reinforcement Learning Based Recommender Systems","created":"2022-03-20","cited_by_count":0,"area":null},{"id":"2203.11011","title":"Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2205.08335","title":"Explanation-Guided Fairness Testing through Genetic Algorithm","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2207.14648","title":"Using Graph Neural Networks for Program Termination","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2302.13268","title":"Revolutionizing Genomics with Reinforcement Learning Techniques","created":"2023-02-26","cited_by_count":0,"area":null},{"id":"2303.09664","title":"Tribe or Not? Critical Inspection of Group Differences Using TribalGram","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2305.18412","title":"Short-term Temporal Dependency Detection under Heterogeneous Event Dynamic with Hawkes Processes","created":"2023-05-28","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":"2308.05385","title":"Adaptive Taxonomy Learning and Historical Patterns Modelling for Patent Classification","created":"2023-08-10","cited_by_count":0,"area":null},{"id":"2310.14976","title":"Reinforcement learning in large, structured action spaces: A simulation study of decision support for spinal cord injury rehabilitation","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2408.01445","title":"MiranDa: Mimicking the Learning Processes of Human Doctors to Achieve Causal Inference for Medication Recommendation","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2408.09410","title":"BernGraph: Probabilistic Graph Neural Networks for EHR-based Medication Recommendations","created":"2024-08-18","cited_by_count":0,"area":null},{"id":"2601.09220","title":"From Hawkes Processes to Attention: Time-Modulated Mechanisms for Event Sequences","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2604.21235","title":"Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.01051","title":"Interaction-Limited Safe Continuous-Time RL for Dynamical Medical Treatment","created":"2026-05-31","cited_by_count":0,"area":null}],"next_cursor":null}