{"total":115,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725,"area":"offlinerl"},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407,"area":null},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327,"area":"offlinerl"},{"id":"2304.02532","title":"Goal-Conditioned Imitation Learning using Score-based Diffusion Policies","created":"2023-04-05","cited_by_count":236,"area":"diffusion"},{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223,"area":"offlinerl"},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175,"area":"offlinerl"},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136,"area":"offlinerl"},{"id":"2504.13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins","created":"2025-04-17","cited_by_count":121,"area":null},{"id":"2410.24185","title":"DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning","created":"2024-10-31","cited_by_count":116,"area":"offlinerl"},{"id":"2012.06733","title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","created":"2020-12-12","cited_by_count":112,"area":"offlinerl"},{"id":"2305.13122","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","created":"2023-05-22","cited_by_count":112,"area":"diffusion"},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108,"area":null},{"id":"2210.10047","title":"From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data","created":"2022-10-18","cited_by_count":103,"area":null},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87,"area":null},{"id":"2010.14500","title":"COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning","created":"2020-10-27","cited_by_count":83,"area":"offlinerl"},{"id":"2109.13841","title":"Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation","created":"2021-09-28","cited_by_count":83,"area":"offlinerl"},{"id":"2201.12716","title":"You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration","created":"2022-01-30","cited_by_count":81,"area":null},{"id":"2209.08959","title":"Latent Plans for Task-Agnostic Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":81,"area":"offlinerl"},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80,"area":null},{"id":"2208.12403","title":"BITS: Bi-level Imitation for Traffic Simulation","created":"2022-08-26","cited_by_count":80,"area":null},{"id":"2210.11435","title":"Learning and Retrieval from Prior Data for Skill-based Imitation Learning","created":"2022-10-20","cited_by_count":77,"area":"offlinerl"},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75,"area":"offlinerl"},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70,"area":null},{"id":"2109.10813","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","created":"2021-09-22","cited_by_count":69,"area":"offlinerl"},{"id":"2409.02920","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)","created":"2024-09-04","cited_by_count":69,"area":null},{"id":"2311.02058","title":"LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery","created":"2023-11-03","cited_by_count":67,"area":"offlinerl"},{"id":"2410.11792","title":"OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation","created":"2024-10-15","cited_by_count":67,"area":null},{"id":"2305.16309","title":"Imitating Task and Motion Planning with Visuomotor Transformers","created":"2023-05-25","cited_by_count":66,"area":"offlinerl"},{"id":"2310.14386","title":"Learning Generalizable Manipulation Policies with Object-Centric 3D Representations","created":"2023-10-22","cited_by_count":61,"area":"offlinerl"},{"id":"2112.05251","title":"Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation","created":"2021-12-09","cited_by_count":59,"area":"offlinerl"},{"id":"2206.10680","title":"Learning Neuro-Symbolic Skills for Bilevel Planning","created":"2022-06-21","cited_by_count":58,"area":null},{"id":"2209.12941","title":"End-to-End Affordance Learning for Robotic Manipulation","created":"2022-09-26","cited_by_count":57,"area":null},{"id":"2410.18907","title":"SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment","created":"2024-10-24","cited_by_count":52,"area":"offlinerl"},{"id":"2205.11790","title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","created":"2022-05-24","cited_by_count":50,"area":"offlinerl"},{"id":"2207.07560","title":"Skill-based Model-based Reinforcement Learning","created":"2022-07-15","cited_by_count":50,"area":null},{"id":"2405.20321","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","created":"2024-05-30","cited_by_count":50,"area":null},{"id":"2503.24361","title":"Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation","created":"2025-03-31","cited_by_count":46,"area":null},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44,"area":"offlinerl"},{"id":"2406.09509","title":"CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making","created":"2024-06-13","cited_by_count":39,"area":"diffusion"},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"area":"lr"},{"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":"2310.16014","title":"Human-in-the-Loop Task and Motion Planning for Imitation Learning","created":"2023-10-24","cited_by_count":29,"area":"offlinerl"},{"id":"2310.08581","title":"Universal Visual Decomposer: Long-Horizon Manipulation Made Easy","created":"2023-10-12","cited_by_count":25,"area":null},{"id":"2405.01472","title":"IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning","created":"2024-05-02","cited_by_count":25,"area":"offlinerl"},{"id":"2103.00375","title":"Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control","created":"2021-02-28","cited_by_count":24,"area":"offlinerl"},{"id":"2203.09749","title":"Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation","created":"2022-03-18","cited_by_count":22,"area":"offlinerl"},{"id":"2504.03515","title":"Dexterous Manipulation through Imitation Learning: A Survey","created":"2025-04-04","cited_by_count":21,"area":"offlinerl"},{"id":"2212.04708","title":"PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection","created":"2022-12-09","cited_by_count":19,"area":null},{"id":"2311.18044","title":"Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challenges","created":"2023-11-29","cited_by_count":18,"area":null},{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"area":"deeprl"},{"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":"2209.10447","title":"Hierarchical Decision Transformer","created":"2022-09-21","cited_by_count":16,"area":"offlinerl"},{"id":"2412.06784","title":"P3-PO: Prescriptive Point Priors for Visuo-Spatial Generalization of Robot Policies","created":"2024-12-09","cited_by_count":16,"area":null},{"id":"2310.14196","title":"Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning","created":"2023-10-22","cited_by_count":15,"area":"offlinerl"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2502.05454","title":"Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following","created":"2025-02-08","cited_by_count":14,"area":null},{"id":"2109.10312","title":"Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks","created":"2021-09-21","cited_by_count":13,"area":null},{"id":"2502.12371","title":"IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation","created":"2025-02-17","cited_by_count":13,"area":"diffusion"},{"id":"2206.04384","title":"Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":12,"area":"wm"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2206.04632","title":"Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations","created":"2022-06-09","cited_by_count":10,"area":"offlinerl"},{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"area":"offlinerl"},{"id":"2410.12124","title":"Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames","created":"2024-10-15","cited_by_count":10,"area":"offlinerl"},{"id":"2503.03998","title":"Robotic Compliant Object Prying Using Diffusion Policy Guided by Vision and Force Observations","created":"2025-03-06","cited_by_count":10,"area":"diffusion"},{"id":"2311.01419","title":"C3DM: Constrained-Context Conditional Diffusion Models for Imitation Learning","created":"2023-11-02","cited_by_count":8,"area":"diffusion"},{"id":"2311.01530","title":"NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptors","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2403.00929","title":"PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning","created":"2024-03-01","cited_by_count":8,"area":"offlinerl"},{"id":"2410.20927","title":"VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions","created":"2024-10-28","cited_by_count":8,"area":"mllm"},{"id":"2312.12036","title":"LHManip: A Dataset for Long-Horizon Language-Grounded Manipulation Tasks in Cluttered Tabletop Environments","created":"2023-12-19","cited_by_count":7,"area":"offlinerl"},{"id":"2410.11584","title":"DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2412.02818","title":"RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields","created":"2024-12-03","cited_by_count":7,"area":"deeprl"},{"id":"2405.05552","title":"Bidirectional Progressive Transformer for Interaction Intention Anticipation","created":"2024-05-09","cited_by_count":6,"area":null},{"id":"2401.17500","title":"LeTO: Learning Constrained Visuomotor Policy with Differentiable Trajectory Optimization","created":"2024-01-30","cited_by_count":5,"area":null},{"id":"2412.07544","title":"Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery","created":"2024-12-10","cited_by_count":5,"area":"offlinerl"},{"id":"2212.02125","title":"TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets","created":"2022-12-05","cited_by_count":4,"area":"offlinerl"},{"id":"2303.12375","title":"Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks","created":"2023-03-22","cited_by_count":4,"area":"offlinerl"},{"id":"2406.15833","title":"XBG: End-to-end Imitation Learning for Autonomous Behaviour in Human-Robot Interaction and Collaboration","created":"2024-06-22","cited_by_count":4,"area":"offlinerl"},{"id":"2505.21652","title":"PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2508.19607","title":"Impedance Primitive-augmented Hierarchical Reinforcement Learning for Sequential Tasks","created":"2025-08-27","cited_by_count":3,"area":"deeprl"},{"id":"2605.05172","title":"When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning","created":"2026-05-06","cited_by_count":3,"area":"offlinerl"},{"id":"2608.25864","title":"MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization","created":"2026-08-26","cited_by_count":3,"area":"vla"},{"id":"2008.01913","title":"Generalization Guarantees for Imitation Learning","created":"2020-08-05","cited_by_count":2,"area":"offlinerl"},{"id":"2202.06027","title":"End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation","created":"2022-02-12","cited_by_count":2,"area":null},{"id":"2303.16427","title":"Learning Excavation of Rigid Objects with Offline Reinforcement Learning","created":"2023-03-29","cited_by_count":2,"area":"offlinerl"},{"id":"2405.06063","title":"A Minimalist Prompt for Zero-Shot Policy Learning","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2503.03056","title":"A2Perf: Real-World Autonomous Agents Benchmark","created":"2025-03-04","cited_by_count":2,"area":"offlinerl"},{"id":"2503.05316","title":"CoinRobot: Generalized End-to-end Robotic Learning for Physical Intelligence","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2503.15035","title":"GraspCorrect: Robotic Grasp Correction via Vision-Language Model-Guided Feedback","created":"2025-03-19","cited_by_count":2,"area":"mllm"},{"id":"2511.00998","title":"GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies","created":"2025-11-02","cited_by_count":2,"area":"diffusion"},{"id":"2511.13710","title":"From Power to Precision: Learning Fine-grained Dexterity for Multi-fingered Robotic Hands","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2606.10025","title":"GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2608.07065","title":"AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies","created":"2026-08-07","cited_by_count":2,"area":"offlinerl"},{"id":"2404.16138","title":"Logic Learning from Demonstrations for Multi-step Manipulation Tasks in Dynamic Environments","created":"2024-04-24","cited_by_count":1,"area":"offlinerl"},{"id":"2408.12593","title":"Automating Deformable Gasket Assembly","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2409.11863","title":"LEMMo-Plan: LLM-Enhanced Learning from Multi-Modal Demonstration for Planning Sequential Contact-Rich Manipulation Tasks","created":"2024-09-18","cited_by_count":1,"area":null},{"id":"2409.15753","title":"Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2507.06404","title":"Learning to Evaluate Autonomous Behaviour in Human-Robot Interaction","created":"2025-07-08","cited_by_count":1,"area":"offlinerl"},{"id":"2509.25466","title":"Data-Efficient Multitask DAgger","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2608.13678","title":"hint$^2$: Hierarchical World Models for Inference-Time Temporal Logic Guidance","created":"2026-08-13","cited_by_count":1,"area":"wm"}],"next_cursor":"100"}