{"total":80,"rows":[{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","cited_by_count":70,"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":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50,"area":"offlinerl"},{"id":"2306.06569","title":"Policy Regularization with Dataset Constraint for Offline Reinforcement Learning","created":"2023-06-11","cited_by_count":34,"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":"2306.12755","title":"Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning","created":"2023-06-22","cited_by_count":27,"area":"offlinerl"},{"id":"2310.17966","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","created":"2023-10-27","cited_by_count":26,"area":"offlinerl"},{"id":"2306.14069","title":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","created":"2023-06-24","cited_by_count":22,"area":"offlinerl"},{"id":"2405.16907","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":22,"area":"offlinerl"},{"id":"2206.07989","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","created":"2022-06-16","cited_by_count":21,"area":"offlinerl"},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"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":"2311.08935","title":"Supported Trust Region Optimization for Offline Reinforcement Learning","created":"2023-11-15","cited_by_count":20,"area":"offlinerl"},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"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":"2410.19400","title":"Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression","created":"2024-10-25","cited_by_count":17,"area":"offlinerl"},{"id":"2301.12130","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2505.08078","title":"What Matters for Batch Online Reinforcement Learning in Robotics?","created":"2025-05-12","cited_by_count":15,"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":"2402.03807","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","created":"2024-02-06","cited_by_count":14,"area":"offlinerl"},{"id":"2304.04660","title":"Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning","created":"2023-04-10","cited_by_count":13,"area":"offlinerl"},{"id":"2403.07262","title":"A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective","created":"2024-03-12","cited_by_count":11,"area":"offlinerl"},{"id":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","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":"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":"2405.14082","title":"Exclusively Penalized Q-learning for Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":8,"area":"offlinerl"},{"id":"2410.24108","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","created":"2024-10-31","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":"2310.18715","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","created":"2023-10-28","cited_by_count":7,"area":"offlinerl"},{"id":"2512.02486","title":"Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts","created":"2025-12-02","cited_by_count":6,"area":"offlinerl"},{"id":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","cited_by_count":6,"area":"offlinerl"},{"id":"2210.04251","title":"State Advantage Weighting for Offline RL","created":"2022-10-09","cited_by_count":5,"area":"offlinerl"},{"id":"2505.19923","title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2512.02350","title":"FOVA: Offline Federated Reinforcement Learning with Mixed-Quality Data","created":"2025-12-02","cited_by_count":5,"area":"offlinerl"},{"id":"2305.13804","title":"OER: Offline Experience Replay for Continual Offline Reinforcement Learning","created":"2023-05-23","cited_by_count":4,"area":"offlinerl"},{"id":"2309.08925","title":"DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning","created":"2023-09-16","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":"2410.20312","title":"Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model","created":"2024-10-27","cited_by_count":4,"area":"offlinerl"},{"id":"2412.20519","title":"Goal-Conditioned Data Augmentation for Offline Reinforcement Learning","created":"2024-12-29","cited_by_count":4,"area":"offlinerl"},{"id":"2501.15085","title":"Data Center Cooling System Optimization Using Offline Reinforcement Learning","created":"2025-01-25","cited_by_count":4,"area":"offlinerl"},{"id":"2602.05051","title":"ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation","created":"2026-02-04","cited_by_count":4,"area":"offlinerl"},{"id":"2307.13824","title":"Offline Reinforcement Learning with On-Policy Q-Function Regularization","created":"2023-07-25","cited_by_count":3,"area":"offlinerl"},{"id":"2310.17245","title":"CROP: Conservative Reward for Model-based Offline Policy Optimization","created":"2023-10-26","cited_by_count":3,"area":"offlinerl"},{"id":"2410.23031","title":"Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation","created":"2024-10-30","cited_by_count":3,"area":"offlinerl"},{"id":"2506.08417","title":"Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood","created":"2025-06-10","cited_by_count":3,"area":"offlinerl"},{"id":"2603.08118","title":"Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting","created":"2026-03-09","cited_by_count":3,"area":"offlinerl"},{"id":"2403.17646","title":"Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning","created":"2024-03-26","cited_by_count":2,"area":"offlinerl"},{"id":"2406.08238","title":"Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning","created":"2024-06-12","cited_by_count":2,"area":"offlinerl"},{"id":"2503.19267","title":"NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic Scenarios","created":"2025-03-25","cited_by_count":2,"area":"offlinerl"},{"id":"2512.02435","title":"Efficient Cross-Domain Offline Reinforcement Learning with Dynamics- and Value-Aligned Data Filtering","created":"2025-12-02","cited_by_count":2,"area":"offlinerl"},{"id":"2306.03680","title":"Mildly Constrained Evaluation Policy for Offline Reinforcement Learning","created":"2023-06-06","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":"2504.03800","title":"Decision SpikeFormer: Spike-Driven Transformer for Decision Making","created":"2025-04-04","cited_by_count":1,"area":"offlinerl"},{"id":"2505.05126","title":"Taming OOD Actions for Offline Reinforcement Learning: An Advantage-Based Approach","created":"2025-05-08","cited_by_count":1,"area":"offlinerl"},{"id":"2505.12211","title":"Imagination-Limited Q-Learning for Offline Reinforcement Learning","created":"2025-05-18","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":"2605.01968","title":"AdamO: A Collapse-Suppressed Optimizer for Offline RL","created":"2026-05-03","cited_by_count":1,"area":"offlinerl"},{"id":"2310.19805","title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration","created":"2023-10-07","cited_by_count":0,"area":"offlinerl"},{"id":"2406.03324","title":"UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning","created":"2024-06-05","cited_by_count":0,"area":"offlinerl"},{"id":"2406.07541","title":"CDSA: Conservative Denoising Score-based Algorithm for Offline Reinforcement Learning","created":"2024-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2410.18626","title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance","created":"2024-10-24","cited_by_count":0,"area":"offlinerl"},{"id":"2412.11253","title":"Are Expressive Models Truly Necessary for Offline RL?","created":"2024-12-15","cited_by_count":0,"area":"offlinerl"},{"id":"2502.00850","title":"Dual Alignment Maximin Optimization for Offline Model-based RL","created":"2025-02-02","cited_by_count":0,"area":"offlinerl"},{"id":"2502.12391","title":"Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL","created":"2025-02-18","cited_by_count":0,"area":"offlinerl"},{"id":"2503.05207","title":"Policy Constraint by Only Support Constraint for Offline Reinforcement Learning","created":"2025-03-07","cited_by_count":0,"area":"offlinerl"},{"id":"2506.00818","title":"Generalized Linear Markov Decision Process","created":"2025-06-01","cited_by_count":0,"area":"offlinerl"},{"id":"2506.15654","title":"CAWR: Corruption-Averse Advantage-Weighted Regression for Robust Policy Optimization","created":"2025-06-18","cited_by_count":0,"area":"offlinerl"},{"id":"2508.05960","title":"Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning","created":"2025-08-08","cited_by_count":0,"area":"offlinerl"},{"id":"2601.01917","title":"Distorted Distributional Policy Evaluation for Offline Reinforcement Learning","created":"2026-01-05","cited_by_count":0,"area":"offlinerl"},{"id":"2601.23010","title":"Automatic Constraint Policy Optimization based on Continuous Constraint Interpolation Framework for Offline Reinforcement Learning","created":"2026-01-30","cited_by_count":0,"area":"offlinerl"},{"id":"2602.07889","title":"Efficient Anti-exploration via VQVAE and Fuzzy Clustering in Offline Reinforcement Learning","created":"2026-02-08","cited_by_count":0,"area":"offlinerl"},{"id":"2605.13054","title":"Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"offlinerl"},{"id":"2605.14779","title":"Peng's Q($\\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning","created":"2026-05-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.24862","title":"Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets","created":"2026-05-24","cited_by_count":0,"area":"offlinerl"},{"id":"2605.29033","title":"Moment Matching Q-Learning","created":"2026-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2606.07550","title":"Offline Reinforcement Learning for Plasma Control in Nuclear Fusion: Codebase and Benchmark","created":"2026-05-19","cited_by_count":0,"area":"offlinerl"},{"id":"2607.02288","title":"Generalization in offline RL: The structure is more important than the amount of pessimism","created":"2026-07-02","cited_by_count":0,"area":"offlinerl"},{"id":"2608.03108","title":"Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RL","created":"2026-08-04","cited_by_count":0,"area":"offlinerl"},{"id":"2609.24489","title":"Lifted Bellman Linear Programming for Offline Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}