{"total":58,"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":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302,"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":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214,"area":"offlinerl"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"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":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76,"area":"offlinerl"},{"id":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"2210.13846","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","created":"2022-10-25","cited_by_count":34,"area":"offlinerl"},{"id":"2310.14550","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation","created":"2023-10-23","cited_by_count":31,"area":"offlinerl"},{"id":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"1905.02780","title":"Uncertainty-Aware Data Aggregation for Deep Imitation Learning","created":"2019-05-07","cited_by_count":20,"area":"offlinerl"},{"id":"2004.10398","title":"Sequential Anomaly Detection using Inverse Reinforcement Learning","created":"2020-04-22","cited_by_count":20,"area":"offlinerl"},{"id":"2306.06871","title":"ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles","created":"2023-06-12","cited_by_count":20,"area":"offlinerl"},{"id":"2111.05440","title":"Dealing with the Unknown: Pessimistic Offline Reinforcement Learning","created":"2021-11-09","cited_by_count":19,"area":"offlinerl"},{"id":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","cited_by_count":14,"area":"offlinerl"},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2211.15612","title":"Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning","created":"2022-11-28","cited_by_count":12,"area":"offlinerl"},{"id":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","cited_by_count":12,"area":"offlinerl"},{"id":"2107.04491","title":"Offline reinforcement learning with uncertainty for treatment strategies in sepsis","created":"2021-07-09","cited_by_count":9,"area":"offlinerl"},{"id":"2110.12468","title":"False Correlation Reduction for Offline Reinforcement Learning","created":"2021-10-24","cited_by_count":9,"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":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"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":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6,"area":"offlinerl"},{"id":"2401.03301","title":"On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling, and Beyond","created":"2024-01-06","cited_by_count":6,"area":"offlinerl"},{"id":"2303.11369","title":"Bridging Imitation and Online Reinforcement Learning: An Optimistic Tale","created":"2023-03-20","cited_by_count":5,"area":"offlinerl"},{"id":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"id":"2110.02304","title":"You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL","created":"2021-10-05","cited_by_count":4,"area":"offlinerl"},{"id":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"id":"2203.10905","title":"Self-Imitation Learning from Demonstrations","created":"2022-03-21","cited_by_count":4,"area":"offlinerl"},{"id":"2310.05723","title":"Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning","created":"2023-10-09","cited_by_count":4,"area":"offlinerl"},{"id":"2109.07275","title":"DROMO: Distributionally Robust Offline Model-based Policy Optimization","created":"2021-09-15","cited_by_count":3,"area":"offlinerl"},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","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":"1912.13037","title":"A New Framework for Query Efficient Active Imitation Learning","created":"2019-12-30","cited_by_count":2,"area":"offlinerl"},{"id":"2105.05473","title":"Interpretable performance analysis towards offline reinforcement learning: A dataset perspective","created":"2021-05-12","cited_by_count":2,"area":"offlinerl"},{"id":"2312.17168","title":"Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?","created":"2023-12-28","cited_by_count":2,"area":"offlinerl"},{"id":"2412.07057","title":"Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning","created":"2024-12-09","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":"2011.14266","title":"Distilled Thompson Sampling: Practical and Efficient Thompson Sampling via Imitation Learning","created":"2020-11-29","cited_by_count":1,"area":"offlinerl"},{"id":"2402.09550","title":"Dataset Clustering for Improved Offline Policy Learning","created":"2024-02-14","cited_by_count":1,"area":"offlinerl"},{"id":"2404.02545","title":"Grid-Mapping Pseudo-Count Constraint for Offline Reinforcement Learning","created":"2024-04-03","cited_by_count":1,"area":"offlinerl"},{"id":"2405.07223","title":"Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning","created":"2024-05-12","cited_by_count":1,"area":"offlinerl"},{"id":"2505.21119","title":"Universal Value-Function Uncertainties","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2511.07629","title":"Partial Action Replacement: Tackling Distribution Shift in Offline MARL","created":"2025-11-10","cited_by_count":1,"area":"offlinerl"},{"id":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"id":"2211.08251","title":"Offline Reinforcement Learning with Adaptive Behavior Regularization","created":"2022-11-15","cited_by_count":0,"area":"offlinerl"},{"id":"2503.06392","title":"EPR-GAIL: An EPR-Enhanced Hierarchical Imitation Learning Framework to Simulate Complex User Consumption Behaviors","created":"2025-03-09","cited_by_count":0,"area":"offlinerl"},{"id":"2505.04897","title":"CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interaction","created":"2025-05-08","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":"2602.23974","title":"Pessimistic Auxiliary Policy for Offline Reinforcement Learning","created":"2026-02-27","cited_by_count":0,"area":"offlinerl"},{"id":"2603.12284","title":"Bayesian Conservative Policy Optimization (BCPO): A Novel Uncertainty-Calibrated Offline Reinforcement Learning with Credible Lower Bounds","created":"2026-03-06","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}