{"total":35,"rows":[{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"2009.07253","title":"Autoregressive Knowledge Distillation through Imitation Learning","created":"2020-09-15","cited_by_count":74,"area":"offlinerl"},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50,"area":"offlinerl"},{"id":"2304.04591","title":"For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal","created":"2023-04-10","cited_by_count":22,"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":"2605.16826","title":"Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation","created":"2026-05-16","cited_by_count":20,"area":"offlinerl"},{"id":"2310.00678","title":"A General Offline Reinforcement Learning Framework for Interactive Recommendation","created":"2023-10-01","cited_by_count":18,"area":"offlinerl"},{"id":"2502.12465","title":"Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification","created":"2025-02-18","cited_by_count":13,"area":"offlinerl"},{"id":"2204.11251","title":"One-Shot Domain-Adaptive Imitation Learning via Progressive Learning","created":"2022-04-24","cited_by_count":6,"area":"offlinerl"},{"id":"1910.12154","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","created":"2019-10-26","cited_by_count":5,"area":"offlinerl"},{"id":"2407.20299","title":"Dataset Distillation for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":5,"area":"offlinerl"},{"id":"2511.18617","title":"AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations","created":"2025-11-23","cited_by_count":4,"area":"offlinerl"},{"id":"2606.30923","title":"Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback","created":"2026-06-29","cited_by_count":4,"area":"offlinerl"},{"id":"2312.07795","title":"Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach","created":"2023-12-12","cited_by_count":3,"area":"offlinerl"},{"id":"2507.19647","title":"GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation Learning","created":"2025-07-25","cited_by_count":3,"area":"offlinerl"},{"id":"2512.23097","title":"A Note on Hybrid Online Reinforcement and Imitation Learning for LLMs: Formulations and Algorithms","created":"2025-12-28","cited_by_count":3,"area":"offlinerl"},{"id":"2301.09770","title":"Language-guided Task Adaptation for Imitation Learning","created":"2023-01-24","cited_by_count":2,"area":"offlinerl"},{"id":"2409.17605","title":"Good Data Is All Imitation Learning Needs","created":"2024-09-26","cited_by_count":2,"area":"offlinerl"},{"id":"2505.20335","title":"Language Model Distillation: A Temporal Difference Imitation Learning Perspective","created":"2025-05-24","cited_by_count":2,"area":"offlinerl"},{"id":"1909.11373","title":"Multi-task Batch Reinforcement Learning with Metric Learning","created":"2019-09-25","cited_by_count":1,"area":"offlinerl"},{"id":"2312.03177","title":"Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learning","created":"2023-12-05","cited_by_count":1,"area":"offlinerl"},{"id":"2406.07041","title":"Integrating Domain Knowledge for handling Limited Data in Offline RL","created":"2024-06-11","cited_by_count":1,"area":"offlinerl"},{"id":"2501.01669","title":"Inversely Learning Transferable Rewards via Abstracted States","created":"2025-01-03","cited_by_count":1,"area":"offlinerl"},{"id":"2603.08763","title":"SPREAD: Subspace Representation Distillation for Lifelong Imitation Learning","created":"2026-03-09","cited_by_count":1,"area":"offlinerl"},{"id":"2202.11325","title":"Reinforcement Learning from Demonstrations by Novel Interactive Expert and Application to Automatic Berthing Control Systems for Unmanned Surface Vessel","created":"2022-02-23","cited_by_count":0,"area":"offlinerl"},{"id":"2406.07117","title":"Augmenting Offline RL with Unlabeled Data","created":"2024-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2503.12761","title":"Analyzing sequential activity and travel decisions with interpretable deep inverse reinforcement learning","created":"2025-03-17","cited_by_count":0,"area":"offlinerl"},{"id":"2511.03565","title":"Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances","created":"2025-11-05","cited_by_count":0,"area":"offlinerl"},{"id":"2512.14726","title":"Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning","created":"2025-12-09","cited_by_count":0,"area":"offlinerl"},{"id":"2603.26249","title":"Knowledge Distillation for Efficient Transformer-Based Reinforcement Learning in Hardware-Constrained Energy Management Systems","created":"2026-03-27","cited_by_count":0,"area":"offlinerl"},{"id":"2605.07166","title":"Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach","created":"2026-05-08","cited_by_count":0,"area":"offlinerl"},{"id":"2607.02034","title":"ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments","created":"2026-07-02","cited_by_count":0,"area":"offlinerl"},{"id":"2610.10601","title":"Teaching a Robot Dog New Tricks: Diverse Quadruped Skills via Combined Reinforcement and Imitation Learning with Adversarial Task Selection","created":"2026-10-06","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}