{"total":20,"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":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29,"area":"offlinerl"},{"id":"2311.00267","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","created":"2023-11-01","cited_by_count":14,"area":"offlinerl"},{"id":"2311.08384","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","created":"2023-11-14","cited_by_count":11,"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":"2306.05726","title":"Iteratively Refined Behavior Regularization for Offline Reinforcement Learning","created":"2023-06-09","cited_by_count":10,"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":"2405.18556","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","created":"2024-05-28","cited_by_count":5,"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":"2306.15503","title":"Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning","created":"2023-06-27","cited_by_count":3,"area":"offlinerl"},{"id":"2603.13971","title":"Chunk-Guided Q-Learning","created":"2026-03-14","cited_by_count":3,"area":"offlinerl"},{"id":"2411.07760","title":"Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning","created":"2024-11-12","cited_by_count":2,"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":"2412.11253","title":"Are Expressive Models Truly Necessary for Offline RL?","created":"2024-12-15","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":"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":"2602.05323","title":"GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL","created":"2026-02-05","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":"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}