{"total":72,"rows":[{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215,"area":"offlinerl"},{"id":"2309.10150","title":"Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions","created":"2023-09-18","cited_by_count":131,"area":"offlinerl"},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"id":"2310.08566","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","created":"2023-10-12","cited_by_count":83,"area":"offlinerl"},{"id":"2407.03162","title":"Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning","created":"2024-07-03","cited_by_count":77,"area":"offlinerl"},{"id":"2306.02437","title":"Data Quality in Imitation Learning","created":"2023-06-04","cited_by_count":75,"area":"offlinerl"},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73,"area":"offlinerl"},{"id":"2212.05711","title":"CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learning","created":"2022-12-12","cited_by_count":71,"area":"offlinerl"},{"id":"2408.15980","title":"In-Context Imitation Learning via Next-Token Prediction","created":"2024-08-28","cited_by_count":70,"area":"offlinerl"},{"id":"2305.16309","title":"Imitating Task and Motion Planning with Visuomotor Transformers","created":"2023-05-25","cited_by_count":66,"area":"offlinerl"},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2306.17237","title":"HYDRA: Hybrid Robot Actions for Imitation Learning","created":"2023-06-29","cited_by_count":55,"area":"offlinerl"},{"id":"2310.05905","title":"TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models","created":"2023-10-09","cited_by_count":53,"area":"offlinerl"},{"id":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50,"area":"offlinerl"},{"id":"2210.13435","title":"Dichotomy of Control: Separating What You Can Control from What You Cannot","created":"2022-10-24","cited_by_count":47,"area":"offlinerl"},{"id":"2305.02968","title":"Masked Trajectory Models for Prediction, Representation, and Control","created":"2023-05-04","cited_by_count":42,"area":"offlinerl"},{"id":"2408.04380","title":"Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations","created":"2024-08-08","cited_by_count":35,"area":"offlinerl"},{"id":"2304.08487","title":"Hyper-Decision Transformer for Efficient Online Policy Adaptation","created":"2023-04-17","cited_by_count":33,"area":"offlinerl"},{"id":"2412.01441","title":"LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations","created":"2024-12-02","cited_by_count":32,"area":"offlinerl"},{"id":"2402.05546","title":"Offline Actor-Critic Reinforcement Learning Scales to Large Models","created":"2024-02-08","cited_by_count":30,"area":"offlinerl"},{"id":"2210.06518","title":"Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories","created":"2022-10-12","cited_by_count":28,"area":"offlinerl"},{"id":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","cited_by_count":26,"area":"offlinerl"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2505.10251","title":"SRT-H: A Hierarchical Framework for Autonomous Surgery via Language Conditioned Imitation Learning","created":"2025-05-15","cited_by_count":26,"area":"offlinerl"},{"id":"2206.05314","title":"Large-Scale Retrieval for Reinforcement Learning","created":"2022-06-10","cited_by_count":24,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2310.12077","title":"One-Shot Imitation Learning: A Pose Estimation Perspective","created":"2023-10-18","cited_by_count":21,"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":"2306.09459","title":"Recurrent Action Transformer with Memory","created":"2023-06-15","cited_by_count":17,"area":"offlinerl"},{"id":"2402.02429","title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","created":"2024-02-04","cited_by_count":17,"area":"offlinerl"},{"id":"2403.06826","title":"In-context Exploration-Exploitation for Reinforcement Learning","created":"2024-03-11","cited_by_count":16,"area":"offlinerl"},{"id":"2303.07551","title":"Merging Decision Transformers: Weight Averaging for Forming Multi-Task Policies","created":"2023-03-14","cited_by_count":15,"area":"offlinerl"},{"id":"2211.14655","title":"How Crucial is Transformer in Decision Transformer?","created":"2022-11-26","cited_by_count":14,"area":"offlinerl"},{"id":"2311.00267","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","created":"2023-11-01","cited_by_count":14,"area":"offlinerl"},{"id":"2401.03306","title":"MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning","created":"2024-01-06","cited_by_count":14,"area":"offlinerl"},{"id":"2307.03406","title":"Goal-Conditioned Predictive Coding for Offline Reinforcement Learning","created":"2023-07-07","cited_by_count":10,"area":"offlinerl"},{"id":"2309.10790","title":"Guide Your Agent with Adaptive Multimodal Rewards","created":"2023-09-19","cited_by_count":10,"area":"offlinerl"},{"id":"2406.05064","title":"Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learning","created":"2024-06-07","cited_by_count":10,"area":"offlinerl"},{"id":"2509.01657","title":"Data Retrieval with Importance Weights for Few-Shot Imitation Learning","created":"2025-09-01","cited_by_count":10,"area":"offlinerl"},{"id":"2210.05158","title":"Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learning","created":"2022-10-11","cited_by_count":6,"area":"offlinerl"},{"id":"2312.02312","title":"Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games","created":"2023-12-04","cited_by_count":6,"area":"offlinerl"},{"id":"2411.01168","title":"Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization","created":"2024-11-02","cited_by_count":6,"area":"offlinerl"},{"id":"2403.18454","title":"Scaling Vision-and-Language Navigation With Offline RL","created":"2024-03-27","cited_by_count":5,"area":"offlinerl"},{"id":"2404.02407","title":"Decision Transformer as a Foundation Model for Partially Observable Continuous Control","created":"2024-04-03","cited_by_count":5,"area":"offlinerl"},{"id":"2508.01131","title":"COLLAGE: Adaptive Fusion-based Retrieval for Augmented Policy Learning","created":"2025-08-02","cited_by_count":5,"area":"offlinerl"},{"id":"2408.11048","title":"RP1M: A Large-Scale Motion Dataset for Piano Playing with Bi-Manual Dexterous Robot Hands","created":"2024-08-20","cited_by_count":4,"area":"offlinerl"},{"id":"2504.04395","title":"Human-Level Competitive Pok\\'emon via Scalable Offline Reinforcement Learning with Transformers","created":"2025-04-06","cited_by_count":4,"area":"offlinerl"},{"id":"2211.16838","title":"Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation","created":"2022-11-30","cited_by_count":3,"area":"offlinerl"},{"id":"2410.08751","title":"Zero-Shot Offline Imitation Learning via Optimal Transport","created":"2024-10-11","cited_by_count":3,"area":"offlinerl"},{"id":"2506.12815","title":"TrojanTO: Action-Level Backdoor Attacks against Trajectory Optimization Models","created":"2025-06-15","cited_by_count":3,"area":"offlinerl"},{"id":"2508.17449","title":"Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges","created":"2025-08-24","cited_by_count":3,"area":"offlinerl"},{"id":"2605.09989","title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","created":"2026-05-11","cited_by_count":3,"area":"offlinerl"},{"id":"2403.18222","title":"Uncertainty-Aware Deployment of Pre-trained Language-Conditioned Imitation Learning Policies","created":"2024-03-27","cited_by_count":2,"area":"offlinerl"},{"id":"2502.04979","title":"Prompt Tuning Decision Transformers with Structured and Scalable Bandits","created":"2025-02-07","cited_by_count":2,"area":"offlinerl"},{"id":"2304.09825","title":"Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments","created":"2023-04-18","cited_by_count":1,"area":"offlinerl"},{"id":"2411.01146","title":"Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","created":"2024-11-02","cited_by_count":1,"area":"offlinerl"},{"id":"2509.24067","title":"In-Context Compositional Q-Learning for Offline Reinforcement Learning","created":"2025-09-28","cited_by_count":1,"area":"offlinerl"},{"id":"2510.17059","title":"Consistent Zero-Shot Imitation with Contrastive Goal Inference","created":"2025-10-20","cited_by_count":1,"area":"offlinerl"},{"id":"2511.07942","title":"Balance Equation-based Distributionally Robust Offline Imitation Learning","created":"2025-11-11","cited_by_count":1,"area":"offlinerl"},{"id":"2602.01018","title":"Offline Discovery of Interpretable Skills from Multi-Task Trajectories","created":"2026-02-01","cited_by_count":1,"area":"offlinerl"},{"id":"2605.06470","title":"Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies","created":"2026-05-07","cited_by_count":1,"area":"offlinerl"},{"id":"2407.01310","title":"Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action Spaces","created":"2024-07-01","cited_by_count":0,"area":"offlinerl"},{"id":"2409.18768","title":"Learning from Demonstration with Implicit Nonlinear Dynamics Models","created":"2024-09-27","cited_by_count":0,"area":"offlinerl"},{"id":"2412.05675","title":"M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model","created":"2024-12-07","cited_by_count":0,"area":"offlinerl"},{"id":"2502.06358","title":"Prompt-Tuning Bandits: Enabling Few-Shot Generalization for Efficient Multi-Task Offline RL","created":"2025-02-10","cited_by_count":0,"area":"offlinerl"},{"id":"2502.10473","title":"Diverse Transformer Decoding for Offline Reinforcement Learning Using Financial Algorithmic Approaches","created":"2025-02-13","cited_by_count":0,"area":"offlinerl"},{"id":"2507.06701","title":"Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement","created":"2025-07-09","cited_by_count":0,"area":"offlinerl"},{"id":"2508.05310","title":"ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning","created":"2025-08-07","cited_by_count":0,"area":"offlinerl"},{"id":"2603.03960","title":"Structural Action Transformer for 3D Dexterous Manipulation","created":"2026-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2608.22591","title":"WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning","created":"2026-08-23","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35880","title":"From Static Policies to Adaptive Priors in Offline Reinforcement Learning","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}