{"total":452,"rows":[{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568,"area":"offlinerl"},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293,"area":"offlinerl"},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551,"area":null},{"id":"2401.02117","title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","created":"2024-01-04","cited_by_count":391,"area":"offlinerl"},{"id":"2410.12557","title":"One Step Diffusion via Shortcut Models","created":"2024-10-16","cited_by_count":391,"area":"diffusion"},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325,"area":"diffusion"},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"2402.10885","title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","created":"2024-02-16","cited_by_count":282,"area":"diffusion"},{"id":"2409.00588","title":"Diffusion Policy Policy Optimization","created":"2024-09-01","cited_by_count":280,"area":"diffusion"},{"id":"2301.10677","title":"Imitating Human Behaviour with Diffusion Models","created":"2023-01-25","cited_by_count":263,"area":"diffusion"},{"id":"2310.07896","title":"NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration","created":"2023-10-11","cited_by_count":248,"area":"diffusion"},{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"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":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218,"area":null},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205,"area":null},{"id":"2405.07503","title":"Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation","created":"2024-05-13","cited_by_count":166,"area":"diffusion"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2403.03181","title":"Behavior Generation with Latent Actions","created":"2024-03-05","cited_by_count":160,"area":"diffusion"},{"id":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156,"area":null},{"id":"2112.01511","title":"The Surprising Effectiveness of Representation Learning for Visual Imitation","created":"2021-12-02","cited_by_count":154,"area":"offlinerl"},{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148,"area":"offlinerl"},{"id":"2403.03949","title":"Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation","created":"2024-03-06","cited_by_count":144,"area":"offlinerl"},{"id":"2403.03954","title":"3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations","created":"2024-03-06","cited_by_count":116,"area":"diffusion"},{"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":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101,"area":null},{"id":"2406.14540","title":"IRASim: A Fine-Grained World Model for Robot Manipulation","created":"2024-06-20","cited_by_count":100,"area":"wm"},{"id":"2209.04899","title":"Instruction-driven history-aware policies for robotic manipulations","created":"2022-09-11","cited_by_count":94,"area":null},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"id":"2410.21257","title":"One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation","created":"2024-10-28","cited_by_count":89,"area":"diffusion"},{"id":"2209.08959","title":"Latent Plans for Task-Agnostic Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":81,"area":"offlinerl"},{"id":"2208.12403","title":"BITS: Bi-level Imitation for Traffic Simulation","created":"2022-08-26","cited_by_count":80,"area":null},{"id":"2203.13251","title":"Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulation","created":"2022-03-24","cited_by_count":78,"area":"offlinerl"},{"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":"2303.01497","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","created":"2023-03-02","cited_by_count":75,"area":"offlinerl"},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75,"area":"offlinerl"},{"id":"2407.01479","title":"EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning","created":"2024-07-01","cited_by_count":75,"area":"diffusion"},{"id":"2410.10088","title":"The Ingredients for Robotic Diffusion Transformers","created":"2024-10-14","cited_by_count":73,"area":"diffusion"},{"id":"2410.24091","title":"3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing","created":"2024-10-31","cited_by_count":72,"area":null},{"id":"2408.15980","title":"In-Context Imitation Learning via Next-Token Prediction","created":"2024-08-28","cited_by_count":70,"area":"offlinerl"},{"id":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","cited_by_count":70,"area":"offlinerl"},{"id":"2407.01812","title":"Equivariant Diffusion Policy","created":"2024-07-01","cited_by_count":66,"area":"diffusion"},{"id":"2503.21860","title":"ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning","created":"2025-03-27","cited_by_count":66,"area":null},{"id":"2409.07343","title":"Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching","created":"2024-09-11","cited_by_count":65,"area":"diffusion"},{"id":"2205.13554","title":"Training and Inference on Any-Order Autoregressive Models the Right Way","created":"2022-05-26","cited_by_count":64,"area":null},{"id":"2202.11855","title":"Learning Multi-Object Dynamics with Compositional Neural Radiance Fields","created":"2022-02-24","cited_by_count":63,"area":null},{"id":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63,"area":"offlinerl"},{"id":"2303.12076","title":"Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Play","created":"2023-03-21","cited_by_count":62,"area":null},{"id":"2307.14326","title":"Waypoint-Based Imitation Learning for Robotic Manipulation","created":"2023-07-26","cited_by_count":61,"area":"offlinerl"},{"id":"2206.10680","title":"Learning Neuro-Symbolic Skills for Bilevel Planning","created":"2022-06-21","cited_by_count":58,"area":null},{"id":"2210.06463","title":"Holo-Dex: Teaching Dexterity with Immersive Mixed Reality","created":"2022-10-12","cited_by_count":57,"area":null},{"id":"2206.08321","title":"Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning","created":"2022-06-16","cited_by_count":56,"area":null},{"id":"2306.17237","title":"HYDRA: Hybrid Robot Actions for Imitation Learning","created":"2023-06-29","cited_by_count":55,"area":"offlinerl"},{"id":"2409.01083","title":"Affordance-based Robot Manipulation with Flow Matching","created":"2024-09-02","cited_by_count":54,"area":"diffusion"},{"id":"2402.14606","title":"Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations","created":"2024-02-22","cited_by_count":53,"area":"offlinerl"},{"id":"2408.17355","title":"Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling","created":"2024-08-30","cited_by_count":52,"area":null},{"id":"2202.01288","title":"Imitation Learning by Estimating Expertise of Demonstrators","created":"2022-02-02","cited_by_count":50,"area":"offlinerl"},{"id":"2402.04292","title":"AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies","created":"2024-02-06","cited_by_count":50,"area":"offlinerl"},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2409.12192","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","created":"2024-09-18","cited_by_count":44,"area":"offlinerl"},{"id":"2405.19690","title":"Diffusion Policies creating a Trust Region for Offline Reinforcement Learning","created":"2024-05-30","cited_by_count":43,"area":"diffusion"},{"id":"2307.04726","title":"Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning","created":"2023-07-10","cited_by_count":42,"area":"diffusion"},{"id":"2504.08438","title":"Diffusion Models for Robotic Manipulation: A Survey","created":"2025-04-11","cited_by_count":41,"area":"diffusion"},{"id":"2307.01849","title":"Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning","created":"2023-07-04","cited_by_count":40,"area":"diffusion"},{"id":"2312.10008","title":"Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects","created":"2023-12-15","cited_by_count":40,"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":"2505.21851","title":"Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories","created":"2025-05-28","cited_by_count":39,"area":"diffusion"},{"id":"2302.13335","title":"Diffusion Model-Augmented Behavioral Cloning","created":"2023-02-26","cited_by_count":38,"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":"2506.06199","title":"3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model","created":"2025-06-06","cited_by_count":37,"area":"wm"},{"id":"2410.07554","title":"ForceMimic: Force-Centric Imitation Learning with Force-Motion Capture System for Contact-Rich Manipulation","created":"2024-10-10","cited_by_count":36,"area":"offlinerl"},{"id":"2512.01809","title":"Much Ado About Noising: Dispelling the Myths of Generative Robotic Control","created":"2025-12-01","cited_by_count":36,"area":null},{"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":"2408.11537","title":"A Survey of Embodied Learning for Object-Centric Robotic Manipulation","created":"2024-08-21","cited_by_count":35,"area":null},{"id":"2412.19948","title":"Motion Planning Diffusion: Learning and Adapting Robot Motion Planning with Diffusion Models","created":"2024-12-27","cited_by_count":33,"area":"diffusion"},{"id":"2205.11027","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","created":"2022-05-23","cited_by_count":31,"area":"offlinerl"},{"id":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30,"area":"lr"},{"id":"2602.03310","title":"RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization","created":"2026-02-03","cited_by_count":30,"area":"vla"},{"id":"2209.10780","title":"Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation","created":"2022-09-22","cited_by_count":29,"area":null},{"id":"2307.04751","title":"Shelving, Stacking, Hanging: Relational Pose Diffusion for Multi-modal Rearrangement","created":"2023-07-10","cited_by_count":29,"area":null},{"id":"2310.12972","title":"CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning","created":"2023-10-19","cited_by_count":29,"area":"offlinerl"},{"id":"2406.05216","title":"TabPFGen -- Tabular Data Generation with TabPFN","created":"2024-06-07","cited_by_count":28,"area":null},{"id":"2209.03277","title":"K-VIL: Keypoints-based Visual Imitation Learning","created":"2022-09-07","cited_by_count":27,"area":"offlinerl"},{"id":"2412.06782","title":"CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction","created":"2024-12-09","cited_by_count":27,"area":null},{"id":"2509.14117","title":"GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model","created":"2025-09-17","cited_by_count":26,"area":"vla"},{"id":"2506.10968","title":"Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop","created":"2025-06-12","cited_by_count":25,"area":null},{"id":"2503.11423","title":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation","created":"2025-03-14","cited_by_count":24,"area":"offlinerl"},{"id":"2210.08073","title":"Eliciting Compatible Demonstrations for Multi-Human Imitation Learning","created":"2022-10-14","cited_by_count":23,"area":"offlinerl"},{"id":"2211.00194","title":"SEIL: Simulation-augmented Equivariant Imitation Learning","created":"2022-10-31","cited_by_count":23,"area":"offlinerl"},{"id":"2409.07163","title":"Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models","created":"2024-09-11","cited_by_count":23,"area":"diffusion"},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2302.12244","title":"To the Noise and Back: Diffusion for Shared Autonomy","created":"2023-02-23","cited_by_count":22,"area":"diffusion"},{"id":"2306.13196","title":"DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability","created":"2023-06-22","cited_by_count":22,"area":"diffusion"},{"id":"2411.05273","title":"Real-World Offline Reinforcement Learning from Vision Language Model Feedback","created":"2024-11-08","cited_by_count":22,"area":"mllm"},{"id":"2205.06333","title":"Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations","created":"2022-05-12","cited_by_count":21,"area":null},{"id":"2206.00695","title":"Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL","created":"2022-06-01","cited_by_count":21,"area":"offlinerl"},{"id":"2402.16075","title":"Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion","created":"2024-02-25","cited_by_count":21,"area":"diffusion"}],"next_cursor":"100"}