{"total":41,"rows":[{"id":"2412.13877","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","created":"2024-12-18","cited_by_count":175,"area":"offlinerl"},{"id":"2410.18647","title":"Data Scaling Laws in Imitation Learning for Robotic Manipulation","created":"2024-10-24","cited_by_count":145,"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":"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":"2503.16408","title":"RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints","created":"2025-03-20","cited_by_count":31,"area":"offlinerl"},{"id":"2505.15725","title":"UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning","created":"2025-05-21","cited_by_count":31,"area":"offlinerl"},{"id":"2306.00323","title":"Thought Cloning: Learning to Think while Acting by Imitating Human Thinking","created":"2023-06-01","cited_by_count":30,"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":"2402.10450","title":"PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control","created":"2024-02-16","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":"2503.04877","title":"Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning","created":"2025-03-06","cited_by_count":17,"area":"offlinerl"},{"id":"2506.13762","title":"Touch begins where vision ends: Generalizable policies for contact-rich manipulation","created":"2025-06-16","cited_by_count":14,"area":"offlinerl"},{"id":"2408.10504","title":"QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning","created":"2024-08-20","cited_by_count":10,"area":"offlinerl"},{"id":"2407.20164","title":"Language-Conditioned Offline RL for Multi-Robot Navigation","created":"2024-07-29","cited_by_count":9,"area":"offlinerl"},{"id":"2408.01402","title":"Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer","created":"2024-08-02","cited_by_count":6,"area":"offlinerl"},{"id":"2411.15131","title":"WildLMa: Long Horizon Loco-Manipulation in the Wild","created":"2024-11-22","cited_by_count":6,"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":"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":"2509.19658","title":"RoboSSM: Scalable In-context Imitation Learning via State-Space Models","created":"2025-09-24","cited_by_count":5,"area":"offlinerl"},{"id":"2312.00054","title":"Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective","created":"2023-11-29","cited_by_count":4,"area":"offlinerl"},{"id":"2312.17479","title":"Culturally-Attuned Moral Machines: Implicit Learning of Human Value Systems by AI through Inverse Reinforcement Learning","created":"2023-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2503.13171","title":"HybridGen: VLM-Guided Hybrid Planning for Scalable Data Generation of Imitation Learning","created":"2025-03-17","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":"2506.15157","title":"Robust Instant Policy: Leveraging Student's t-Regression Model for Robust In-context Imitation Learning of Robot Manipulation","created":"2025-06-18","cited_by_count":3,"area":"offlinerl"},{"id":"2509.22023","title":"Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error","created":"2025-09-26","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":"2504.01719","title":"Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning","created":"2025-04-02","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":"2310.13004","title":"Progressively Efficient Learning","created":"2023-10-13","cited_by_count":1,"area":"offlinerl"},{"id":"2404.09717","title":"Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model","created":"2024-04-15","cited_by_count":1,"area":"offlinerl"},{"id":"2410.02231","title":"SEAL: SEmantic-Augmented Imitation Learning via Language Model","created":"2024-10-03","cited_by_count":1,"area":"offlinerl"},{"id":"2509.05368","title":"Long-Horizon Visual Imitation Learning via Plan and Code Reflection","created":"2025-09-04","cited_by_count":1,"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":"2603.10929","title":"Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment","created":"2026-03-11","cited_by_count":1,"area":"offlinerl"},{"id":"2607.27549","title":"Cross-Embodiment Transfer via Behavior-Aligned Representations","created":"2026-07-30","cited_by_count":1,"area":"offlinerl"},{"id":"2505.00503","title":"Variational OOD State Correction for Offline Reinforcement Learning","created":"2025-05-01","cited_by_count":0,"area":"offlinerl"},{"id":"2602.18025","title":"Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets","created":"2026-02-20","cited_by_count":0,"area":"offlinerl"},{"id":"2604.14474","title":"Scouting By Reward: VLM-TO-IRL-Driven Player Selection For Esports","created":"2026-04-15","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":"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":"2609.37135","title":"Multi-Granularity Language-Guided Imitation Learning via Instruction Decomposition","created":"2026-09-29","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}