{"total":30,"rows":[{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2411.05193","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","created":"2024-11-07","cited_by_count":10,"area":"offlinerl"},{"id":"2411.07007","title":"Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching","created":"2024-11-11","cited_by_count":10,"area":"offlinerl"},{"id":"2502.06051","title":"Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits","created":"2025-02-09","cited_by_count":10,"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":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2410.01101","title":"Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank","created":"2024-10-01","cited_by_count":6,"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":"2504.15046","title":"Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision","created":"2025-04-21","cited_by_count":5,"area":"offlinerl"},{"id":"2605.00264","title":"Pessimism-Free Offline Learning in General-Sum Games via KL Regularization","created":"2026-04-30","cited_by_count":5,"area":"offlinerl"},{"id":"2501.02330","title":"SR-Reward: Taking The Path More Traveled","created":"2025-01-04","cited_by_count":3,"area":"offlinerl"},{"id":"2501.14199","title":"Coordinating Ride-Pooling with Public Transit using Reward-Guided Conservative Q-Learning: An Offline Training and Online Fine-Tuning Reinforcement Learning Framework","created":"2025-01-24","cited_by_count":3,"area":"offlinerl"},{"id":"2502.07645","title":"From Action Labels to Sets: Rethinking Action Supervision for Imitation Learning from Corrective Feedback","created":"2025-02-11","cited_by_count":3,"area":"offlinerl"},{"id":"2604.00055","title":"Generalizable Dense Reward for Long-Horizon Robotic Tasks","created":"2026-03-31","cited_by_count":3,"area":"offlinerl"},{"id":"2606.30445","title":"When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon","created":"2026-06-29","cited_by_count":3,"area":"offlinerl"},{"id":"2407.00495","title":"A Bayesian Solution To The Imitation Gap","created":"2024-06-29","cited_by_count":2,"area":"offlinerl"},{"id":"2503.11019","title":"Residual Policy Gradient: A Reward View of KL-regularized Objective","created":"2025-03-14","cited_by_count":2,"area":"offlinerl"},{"id":"2506.23090","title":"Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems","created":"2025-06-29","cited_by_count":2,"area":"offlinerl"},{"id":"2601.00167","title":"Online Finetuning Decision Transformers with Pure RL Gradients","created":"2026-01-01","cited_by_count":1,"area":"offlinerl"},{"id":"2602.14844","title":"Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment","created":"2026-02-16","cited_by_count":1,"area":"offlinerl"},{"id":"2505.14820","title":"Imitation Learning via Focused Satisficing","created":"2025-05-20","cited_by_count":0,"area":"offlinerl"},{"id":"2508.04225","title":"Symmetric Behavior Regularized Policy Optimization","created":"2025-08-06","cited_by_count":0,"area":"offlinerl"},{"id":"2509.26294","title":"Noise-Guided Transport for Imitation Learning","created":"2025-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2602.20643","title":"TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer","created":"2026-02-24","cited_by_count":0,"area":"offlinerl"},{"id":"2603.24883","title":"Learning to Staff: Offline Reinforcement Learning and Fine-Tuned LLMs for Warehouse Staffing Optimization","created":"2026-03-25","cited_by_count":0,"area":"offlinerl"},{"id":"2604.13175","title":"Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarization","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.17017","title":"When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited","created":"2026-05-16","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":"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":"2608.20208","title":"RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation","created":"2026-08-20","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}