{"total":98,"rows":[{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114,"area":"offlinerl"},{"id":"2107.09003","title":"Constraints Penalized Q-learning for Safe Offline Reinforcement Learning","created":"2021-07-19","cited_by_count":91,"area":"offlinerl"},{"id":"2110.08695","title":"Towards Instance-Optimal Offline Reinforcement Learning with Pessimism","created":"2021-10-17","cited_by_count":78,"area":"offlinerl"},{"id":"2007.08202","title":"Provably Good Batch Reinforcement Learning Without Great Exploration","created":"2020-07-16","cited_by_count":77,"area":"offlinerl"},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"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":"2203.05804","title":"Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism","created":"2022-03-11","cited_by_count":65,"area":"offlinerl"},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"area":"offlinerl"},{"id":"2102.00714","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","created":"2021-02-01","cited_by_count":63,"area":"offlinerl"},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2102.01748","title":"Near-Optimal Offline Reinforcement Learning via Double Variance Reduction","created":"2021-02-02","cited_by_count":56,"area":"offlinerl"},{"id":"2103.13883","title":"Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning","created":"2021-03-25","cited_by_count":42,"area":"offlinerl"},{"id":"2002.10544","title":"Provable Representation Learning for Imitation Learning via Bi-level Optimization","created":"2020-02-24","cited_by_count":41,"area":"offlinerl"},{"id":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40,"area":"offlinerl"},{"id":"2110.14000","title":"Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning","created":"2021-10-26","cited_by_count":32,"area":"offlinerl"},{"id":"2205.11027","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","created":"2022-05-23","cited_by_count":31,"area":"offlinerl"},{"id":"2105.07351","title":"Model-Based Offline Planning with Trajectory Pruning","created":"2021-05-16","cited_by_count":30,"area":"offlinerl"},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29,"area":"offlinerl"},{"id":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"area":"offlinerl"},{"id":"2306.00603","title":"Safe Offline Reinforcement Learning with Real-Time Budget Constraints","created":"2023-06-01","cited_by_count":28,"area":"offlinerl"},{"id":"2102.09225","title":"Continuous Doubly Constrained Batch Reinforcement Learning","created":"2021-02-18","cited_by_count":27,"area":"offlinerl"},{"id":"2011.04019","title":"Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient","created":"2020-11-08","cited_by_count":24,"area":"offlinerl"},{"id":"2110.04156","title":"Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters","created":"2021-10-08","cited_by_count":24,"area":"offlinerl"},{"id":"2106.00099","title":"Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs","created":"2021-05-31","cited_by_count":22,"area":"offlinerl"},{"id":"2208.04560","title":"Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems","created":"2022-08-09","cited_by_count":22,"area":"offlinerl"},{"id":"2211.13208","title":"On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation","created":"2022-11-23","cited_by_count":22,"area":"offlinerl"},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2306.04220","title":"Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL","created":"2023-06-07","cited_by_count":18,"area":"offlinerl"},{"id":"2407.00699","title":"Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning","created":"2024-06-30","cited_by_count":17,"area":"offlinerl"},{"id":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16,"area":"offlinerl"},{"id":"2109.08331","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","created":"2021-09-17","cited_by_count":16,"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":"2210.03802","title":"Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization","created":"2022-10-07","cited_by_count":16,"area":"offlinerl"},{"id":"2301.12203","title":"SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2105.06029","title":"Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings","created":"2021-05-13","cited_by_count":14,"area":"offlinerl"},{"id":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","cited_by_count":14,"area":"offlinerl"},{"id":"2302.00662","title":"Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders","created":"2023-02-01","cited_by_count":13,"area":"offlinerl"},{"id":"2412.18946","title":"Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning","created":"2024-12-25","cited_by_count":13,"area":"offlinerl"},{"id":"2203.01707","title":"Testing Stationarity and Change Point Detection in Reinforcement Learning","created":"2022-03-03","cited_by_count":12,"area":"offlinerl"},{"id":"2210.08642","title":"Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data","created":"2022-10-16","cited_by_count":12,"area":"offlinerl"},{"id":"2202.13163","title":"Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons","created":"2022-02-26","cited_by_count":10,"area":"offlinerl"},{"id":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2412.15429","title":"Offline Safe Reinforcement Learning Using Trajectory Classification","created":"2024-12-19","cited_by_count":9,"area":"offlinerl"},{"id":"2412.18855","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","created":"2024-12-25","cited_by_count":9,"area":"offlinerl"},{"id":"2006.03886","title":"Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning","created":"2020-06-06","cited_by_count":8,"area":"offlinerl"},{"id":"2103.06671","title":"Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks","created":"2021-03-11","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":"2310.18715","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","created":"2023-10-28","cited_by_count":7,"area":"offlinerl"},{"id":"2412.08794","title":"Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning","created":"2024-12-11","cited_by_count":7,"area":"offlinerl"},{"id":"2311.18206","title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","created":"2023-11-30","cited_by_count":6,"area":"offlinerl"},{"id":"2502.08021","title":"Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol","created":"2025-02-11","cited_by_count":6,"area":"offlinerl"},{"id":"2301.11426","title":"Model-based Offline Reinforcement Learning with Local Misspecification","created":"2023-01-26","cited_by_count":5,"area":"offlinerl"},{"id":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"id":"2403.01734","title":"Offline Goal-Conditioned Reinforcement Learning for Safety-Critical Tasks with Recovery Policy","created":"2024-03-04","cited_by_count":5,"area":"offlinerl"},{"id":"2004.08356","title":"Goal-conditioned Batch Reinforcement Learning for Rotation Invariant Locomotion","created":"2020-04-17","cited_by_count":4,"area":"offlinerl"},{"id":"2307.06328","title":"Budgeting Counterfactual for Offline RL","created":"2023-07-12","cited_by_count":4,"area":"offlinerl"},{"id":"2312.17503","title":"HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning","created":"2023-12-29","cited_by_count":4,"area":"offlinerl"},{"id":"2401.00629","title":"Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning","created":"2024-01-01","cited_by_count":4,"area":"offlinerl"},{"id":"2505.09496","title":"Reinforcement Learning for Individual Optimal Policy from Heterogeneous Data","created":"2025-05-14","cited_by_count":4,"area":"offlinerl"},{"id":"2510.01460","title":"The Three Regimes of Offline-to-Online Reinforcement Learning","created":"2025-10-01","cited_by_count":4,"area":"offlinerl"},{"id":"2111.14346","title":"Pessimistic Model Selection for Offline Deep Reinforcement Learning","created":"2021-11-29","cited_by_count":3,"area":"offlinerl"},{"id":"2206.02000","title":"Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning","created":"2022-06-04","cited_by_count":3,"area":"offlinerl"},{"id":"2207.07790","title":"BCRLSP: An Offline Reinforcement Learning Framework for Sequential Targeted Promotion","created":"2022-07-16","cited_by_count":3,"area":"offlinerl"},{"id":"2302.12780","title":"VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation","created":"2023-02-24","cited_by_count":3,"area":"offlinerl"},{"id":"2312.02355","title":"When is Offline Policy Selection Sample Efficient for Reinforcement Learning?","created":"2023-12-04","cited_by_count":3,"area":"offlinerl"},{"id":"2502.20030","title":"Offline Reinforcement Learning via Inverse Optimization","created":"2025-02-27","cited_by_count":3,"area":"offlinerl"},{"id":"2506.14375","title":"Advancing Safe Mechanical Ventilation Using Offline RL With Hybrid Actions and Clinically Aligned Rewards","created":"2025-06-17","cited_by_count":3,"area":"offlinerl"},{"id":"2211.16078","title":"Behavior Estimation from Multi-Source Data for Offline Reinforcement Learning","created":"2022-11-29","cited_by_count":2,"area":"offlinerl"},{"id":"2310.10312","title":"End-to-end Offline Reinforcement Learning for Glycemia Control","created":"2023-10-16","cited_by_count":2,"area":"offlinerl"},{"id":"2503.12283","title":"Towards Optimal Offline Reinforcement Learning","created":"2025-03-15","cited_by_count":2,"area":"offlinerl"},{"id":"2602.06603","title":"The hidden risks of temporal resampling in clinical reinforcement learning","created":"2026-02-06","cited_by_count":2,"area":"offlinerl"},{"id":"2110.03165","title":"Offline RL With Resource Constrained Online Deployment","created":"2021-10-07","cited_by_count":1,"area":"offlinerl"},{"id":"2401.12934","title":"Reward-Relevance-Filtered Linear Offline Reinforcement Learning","created":"2024-01-23","cited_by_count":1,"area":"offlinerl"},{"id":"2406.04534","title":"Strategically Conservative Q-Learning","created":"2024-06-06","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":"2510.22027","title":"Online Optimization for Offline Safe Reinforcement Learning","created":"2025-10-24","cited_by_count":1,"area":"offlinerl"},{"id":"2605.05123","title":"Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning","created":"2026-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2105.13431","title":"An Offline Risk-aware Policy Selection Method for Bayesian Markov Decision Processes","created":"2021-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2212.14405","title":"Offline Policy Optimization in RL with Variance Regularizaton","created":"2022-12-29","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":"2505.19337","title":"Prompting Decision Transformers for Zero-Shot Reach-Avoid Policies","created":"2025-05-25","cited_by_count":0,"area":"offlinerl"},{"id":"2505.22442","title":"Fully Offline Reinforcement Learning","created":"2025-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2509.09655","title":"Feasibility-Guided Fair Adaptive Offline Reinforcement Learning for Medicaid Care Management","created":"2025-09-11","cited_by_count":0,"area":"offlinerl"},{"id":"2509.09772","title":"Hybrid Adaptive Conformal Offline Reinforcement Learning for Fair Population Health Management","created":"2025-09-11","cited_by_count":0,"area":"offlinerl"},{"id":"2510.03494","title":"Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear $q^\\pi$-Realizability and Concentrability","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2512.08012","title":"Benchmarking Offline Multi-Objective Reinforcement Learning in Critical Care","created":"2025-12-08","cited_by_count":0,"area":"offlinerl"},{"id":"2602.02530","title":"Formulating Reinforcement Learning for Human-Robot Collaboration through Off-Policy Evaluation","created":"2026-01-27","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":"2603.11372","title":"Ensuring Safety in Automated Mechanical Ventilation through Offline Reinforcement Learning and Digital Twin Verification","created":"2026-03-11","cited_by_count":0,"area":"offlinerl"},{"id":"2606.19481","title":"Insulin4RL: Real-Time Insulin Management in the Intensive Care Unit for Offline Reinforcement Learning","created":"2026-06-17","cited_by_count":0,"area":"offlinerl"},{"id":"2606.20206","title":"Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random","created":"2026-06-18","cited_by_count":0,"area":"offlinerl"},{"id":"2606.21085","title":"Sim2O: Efficient Offline-to-Online MARL via Joint Action Composition","created":"2026-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2607.15080","title":"Evaluating covariate balance for long time horizon Markov decision processes","created":"2026-07-16","cited_by_count":0,"area":"offlinerl"},{"id":"2608.11410","title":"Unmasking Toxic Mimicry in Medical Offline Reinforcement Learning for ICU Sepsis Management via Counterfactual Clinical Audits","created":"2026-08-11","cited_by_count":0,"area":"offlinerl"},{"id":"2608.28065","title":"Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning","created":"2026-08-28","cited_by_count":0,"area":"offlinerl"},{"id":"2609.34426","title":"Q-learning Penalized Transformer for Safe Offline Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}