{"total":51,"rows":[{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121,"area":"offlinerl"},{"id":"2107.11003","title":"Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings","created":"2021-07-23","cited_by_count":68,"area":"offlinerl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"id":"2210.01808","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":42,"area":"offlinerl"},{"id":"2211.04974","title":"Leveraging Offline Data in Online Reinforcement Learning","created":"2022-11-09","cited_by_count":42,"area":"offlinerl"},{"id":"2007.01174","title":"Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch","created":"2020-07-02","cited_by_count":33,"area":"offlinerl"},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"id":"2210.06692","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","created":"2022-10-13","cited_by_count":22,"area":"offlinerl"},{"id":"2203.09365","title":"Semi-Markov Offline Reinforcement Learning for Healthcare","created":"2022-03-17","cited_by_count":18,"area":"offlinerl"},{"id":"2302.07549","title":"Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications","created":"2023-02-15","cited_by_count":17,"area":"offlinerl"},{"id":"2210.02552","title":"Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning","created":"2022-10-05","cited_by_count":16,"area":"offlinerl"},{"id":"2307.11352","title":"Model-based Offline Reinforcement Learning with Count-based Conservatism","created":"2023-07-21","cited_by_count":16,"area":"offlinerl"},{"id":"2403.12946","title":"Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes","created":"2024-03-19","cited_by_count":14,"area":"offlinerl"},{"id":"2210.01282","title":"Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":12,"area":"offlinerl"},{"id":"2303.14716","title":"Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning","created":"2023-03-26","cited_by_count":12,"area":"offlinerl"},{"id":"2201.12594","title":"Robust Imitation Learning from Corrupted Demonstrations","created":"2022-01-29","cited_by_count":10,"area":"offlinerl"},{"id":"2312.03991","title":"MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator","created":"2023-12-07","cited_by_count":9,"area":"offlinerl"},{"id":"2406.12550","title":"Offline Imitation Learning with Model-based Reverse Augmentation","created":"2024-06-18","cited_by_count":8,"area":"offlinerl"},{"id":"2411.00465","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","created":"2024-11-01","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":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"id":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"id":"2405.18556","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","created":"2024-05-28","cited_by_count":5,"area":"offlinerl"},{"id":"2106.09256","title":"Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning","created":"2021-06-17","cited_by_count":4,"area":"offlinerl"},{"id":"2506.09574","title":"MOORL: A Framework for Integrating Offline-Online Reinforcement Learning","created":"2025-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2305.13289","title":"Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach","created":"2023-05-22","cited_by_count":3,"area":"offlinerl"},{"id":"2404.16399","title":"Offline Reinforcement Learning with Behavioral Supervisor Tuning","created":"2024-04-25","cited_by_count":3,"area":"offlinerl"},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","cited_by_count":3,"area":"offlinerl"},{"id":"2411.11088","title":"An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces","created":"2024-11-17","cited_by_count":3,"area":"offlinerl"},{"id":"2505.20621","title":"Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learning","created":"2025-05-27","cited_by_count":3,"area":"offlinerl"},{"id":"2310.01616","title":"Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity","created":"2023-10-02","cited_by_count":2,"area":"offlinerl"},{"id":"2503.20285","title":"Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation","created":"2025-03-26","cited_by_count":2,"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":"2407.01837","title":"To Switch or Not to Switch? Balanced Policy Switching in Offline Reinforcement Learning","created":"2024-07-01","cited_by_count":1,"area":"offlinerl"},{"id":"2502.11480","title":"Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspective","created":"2025-02-17","cited_by_count":1,"area":"offlinerl"},{"id":"2506.08463","title":"How to Provably Improve Return Conditioned Supervised Learning?","created":"2025-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2507.12815","title":"From Novelty to Imitation: Self-Distilled Rewards for Offline Reinforcement Learning","created":"2025-07-17","cited_by_count":1,"area":"offlinerl"},{"id":"2511.12075","title":"Treatment Stitching with Schr\\\"odinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies","created":"2025-11-15","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":"2306.14063","title":"Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data","created":"2023-06-24","cited_by_count":0,"area":"offlinerl"},{"id":"2411.04534","title":"Hypercube Policy Regularization Framework for Offline Reinforcement Learning","created":"2024-11-07","cited_by_count":0,"area":"offlinerl"},{"id":"2509.00347","title":"LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning","created":"2025-08-30","cited_by_count":0,"area":"offlinerl"},{"id":"2511.11973","title":"Quantile Q-Learning: Revisiting Offline Extreme Q-Learning with Quantile Regression","created":"2025-11-15","cited_by_count":0,"area":"offlinerl"},{"id":"2602.00629","title":"Action-Free Offline-to-Online RL via Discretised State Policies","created":"2026-01-31","cited_by_count":0,"area":"offlinerl"},{"id":"2602.01260","title":"Sample Efficient Active Algorithms for Offline Reinforcement Learning","created":"2026-02-01","cited_by_count":0,"area":"offlinerl"},{"id":"2602.17312","title":"LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy","created":"2026-02-19","cited_by_count":0,"area":"offlinerl"},{"id":"2605.09818","title":"Learning to Compress Time-to-Control: A Reinforcement Learning Framework for Chronic Disease Management","created":"2026-05-10","cited_by_count":0,"area":"offlinerl"},{"id":"2605.14497","title":"ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization","created":"2026-05-14","cited_by_count":0,"area":"offlinerl"},{"id":"2608.22284","title":"Learning from the Test: Self-Referential Differential Testing for Deep RL Agents","created":"2026-08-23","cited_by_count":0,"area":"offlinerl"},{"id":"2610.16984","title":"From Suboptimal to Optimal: One-Step Latent Flow Policies for Offline Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}