{"total":41,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"area":"offlinerl"},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111,"area":"offlinerl"},{"id":"1807.08364","title":"EnsembleDAgger: A Bayesian Approach to Safe Imitation Learning","created":"2018-07-22","cited_by_count":100,"area":"offlinerl"},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"2105.06411","title":"Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration","created":"2021-05-13","cited_by_count":93,"area":"offlinerl"},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73,"area":"offlinerl"},{"id":"2410.04640","title":"Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress","created":"2024-10-06","cited_by_count":69,"area":"offlinerl"},{"id":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50,"area":"offlinerl"},{"id":"2004.10398","title":"Sequential Anomaly Detection using Inverse Reinforcement Learning","created":"2020-04-22","cited_by_count":20,"area":"offlinerl"},{"id":"2107.09251","title":"Offline Preference-Based Apprenticeship Learning","created":"2021-07-20","cited_by_count":17,"area":"offlinerl"},{"id":"1803.10231","title":"Safe end-to-end imitation learning for model predictive control","created":"2018-03-27","cited_by_count":12,"area":"offlinerl"},{"id":"1904.08377","title":"Gaze Training by Modulated Dropout Improves Imitation Learning","created":"2019-04-17","cited_by_count":10,"area":"offlinerl"},{"id":"2102.11327","title":"Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learning","created":"2021-02-22","cited_by_count":10,"area":"offlinerl"},{"id":"2410.05026","title":"Active Fine-Tuning of Multi-Task Policies","created":"2024-10-07","cited_by_count":9,"area":"offlinerl"},{"id":"2008.12969","title":"Driving Through Ghosts: Behavioral Cloning with False Positives","created":"2020-08-29","cited_by_count":8,"area":"offlinerl"},{"id":"2306.07541","title":"A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning","created":"2023-06-13","cited_by_count":8,"area":"offlinerl"},{"id":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2404.19346","title":"Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning","created":"2024-04-30","cited_by_count":7,"area":"offlinerl"},{"id":"2604.13788","title":"Failure Identification in Imitation Learning Via Statistical and Semantic Filtering","created":"2026-04-15","cited_by_count":6,"area":"offlinerl"},{"id":"2011.09586","title":"SAFARI: Safe and Active Robot Imitation Learning with Imagination","created":"2020-11-18","cited_by_count":5,"area":"offlinerl"},{"id":"2006.07777","title":"Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms","created":"2020-06-14","cited_by_count":4,"area":"offlinerl"},{"id":"2206.01085","title":"Incorporating Explicit Uncertainty Estimates into Deep Offline Reinforcement Learning","created":"2022-06-02","cited_by_count":4,"area":"offlinerl"},{"id":"1911.11744","title":"Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration","created":"2019-11-26","cited_by_count":3,"area":"offlinerl"},{"id":"2503.11339","title":"Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model","created":"2025-03-14","cited_by_count":3,"area":"offlinerl"},{"id":"2602.19917","title":"Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning","created":"2026-02-23","cited_by_count":3,"area":"offlinerl"},{"id":"1906.04813","title":"Towards Inverse Reinforcement Learning for Limit Order Book Dynamics","created":"2019-06-11","cited_by_count":2,"area":"offlinerl"},{"id":"2405.11139","title":"RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution Shifts","created":"2024-05-18","cited_by_count":2,"area":"offlinerl"},{"id":"2509.03790","title":"What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?","created":"2025-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"1903.05697","title":"Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks","created":"2019-03-13","cited_by_count":1,"area":"offlinerl"},{"id":"2510.09096","title":"When a Robot is More Capable than a Human: Learning from Constrained Demonstrators","created":"2025-10-10","cited_by_count":1,"area":"offlinerl"},{"id":"2605.08202","title":"Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning","created":"2026-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2609.08123","title":"DISEIL: Demonstration Distillation for Sample-Efficient Imitation Learning","created":"2026-09-08","cited_by_count":1,"area":"offlinerl"},{"id":"2003.01283","title":"MPC-guided Imitation Learning of Neural Network Policies for the Artificial Pancreas","created":"2020-03-03","cited_by_count":0,"area":"offlinerl"},{"id":"2404.06188","title":"Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning","created":"2024-04-09","cited_by_count":0,"area":"offlinerl"},{"id":"2508.05310","title":"ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning","created":"2025-08-07","cited_by_count":0,"area":"offlinerl"},{"id":"2512.14726","title":"Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning","created":"2025-12-09","cited_by_count":0,"area":"offlinerl"},{"id":"2601.18107","title":"Beyond Static Datasets: Robust Offline Policy Optimization via Vetted Synthetic Transitions","created":"2026-01-26","cited_by_count":0,"area":"offlinerl"},{"id":"2610.15428","title":"Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning","created":"2026-10-11","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}