{"total":131,"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":"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":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"2302.12422","title":"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play","created":"2023-02-24","cited_by_count":223,"area":"offlinerl"},{"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":"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":"2209.08959","title":"Latent Plans for Task-Agnostic Offline Reinforcement Learning","created":"2022-09-19","cited_by_count":81,"area":"offlinerl"},{"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":"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":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63,"area":"offlinerl"},{"id":"2307.14326","title":"Waypoint-Based Imitation Learning for Robotic Manipulation","created":"2023-07-26","cited_by_count":61,"area":"offlinerl"},{"id":"2306.17237","title":"HYDRA: Hybrid Robot Actions for Imitation Learning","created":"2023-06-29","cited_by_count":55,"area":"offlinerl"},{"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":"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":"2312.10008","title":"Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects","created":"2023-12-15","cited_by_count":40,"area":"offlinerl"},{"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":"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":"2205.11027","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","created":"2022-05-23","cited_by_count":31,"area":"offlinerl"},{"id":"2310.12972","title":"CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning","created":"2023-10-19","cited_by_count":29,"area":"offlinerl"},{"id":"2209.03277","title":"K-VIL: Keypoints-based Visual Imitation Learning","created":"2022-09-07","cited_by_count":27,"area":"offlinerl"},{"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":"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":"2501.14400","title":"SKIL: Semantic Keypoint Imitation Learning for Generalizable Data-efficient Manipulation","created":"2025-01-24","cited_by_count":21,"area":"offlinerl"},{"id":"2504.03515","title":"Dexterous Manipulation through Imitation Learning: A Survey","created":"2025-04-04","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":"2207.00244","title":"Discriminator-Guided Model-Based Offline Imitation Learning","created":"2022-07-01","cited_by_count":17,"area":"offlinerl"},{"id":"2210.06479","title":"Real World Offline Reinforcement Learning with Realistic Data Source","created":"2022-10-12","cited_by_count":17,"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":"2211.11603","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","created":"2022-11-21","cited_by_count":15,"area":"offlinerl"},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15,"area":"offlinerl"},{"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":"2405.05439","title":"How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation","created":"2024-05-08","cited_by_count":15,"area":"offlinerl"},{"id":"2202.07600","title":"Bayesian Imitation Learning for End-to-End Mobile Manipulation","created":"2022-02-15","cited_by_count":14,"area":"offlinerl"},{"id":"2310.06171","title":"Memory-Consistent Neural Networks for Imitation Learning","created":"2023-10-09","cited_by_count":14,"area":"offlinerl"},{"id":"2310.12238","title":"Few-Shot In-Context Imitation Learning via Implicit Graph Alignment","created":"2023-10-18","cited_by_count":14,"area":"offlinerl"},{"id":"2503.10966","title":"Is Your Imitation Learning Policy Better than Mine? Policy Comparison with Near-Optimal Stopping","created":"2025-03-14","cited_by_count":14,"area":"offlinerl"},{"id":"2506.13498","title":"A Survey on Imitation Learning for Contact-Rich Tasks in Robotics","created":"2025-06-16","cited_by_count":14,"area":"offlinerl"},{"id":"2306.14534","title":"CEIL: Generalized Contextual Imitation Learning","created":"2023-06-26","cited_by_count":13,"area":"offlinerl"},{"id":"2405.17476","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","created":"2024-05-24","cited_by_count":12,"area":"offlinerl"},{"id":"2410.18065","title":"SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation","created":"2024-10-23","cited_by_count":11,"area":"offlinerl"},{"id":"2202.10765","title":"Transporters with Visual Foresight for Solving Unseen Rearrangement Tasks","created":"2022-02-22","cited_by_count":9,"area":"offlinerl"},{"id":"2505.22626","title":"SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning","created":"2025-05-28","cited_by_count":9,"area":"offlinerl"},{"id":"2301.11734","title":"Improving Behavioural Cloning with Positive Unlabeled Learning","created":"2023-01-27","cited_by_count":8,"area":"offlinerl"},{"id":"2408.06536","title":"A Comparison of Imitation Learning Algorithms for Bimanual Manipulation","created":"2024-08-13","cited_by_count":8,"area":"offlinerl"},{"id":"2411.03294","title":"Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learning","created":"2024-11-05","cited_by_count":7,"area":"offlinerl"},{"id":"2208.00088","title":"Improved Policy Optimization for Online Imitation Learning","created":"2022-07-29","cited_by_count":6,"area":"offlinerl"},{"id":"2303.02646","title":"Seq2Seq Imitation Learning for Tactile Feedback-based Manipulation","created":"2023-03-05","cited_by_count":6,"area":"offlinerl"},{"id":"2306.15156","title":"Learning non-Markovian Decision-Making from State-only Sequences","created":"2023-06-27","cited_by_count":6,"area":"offlinerl"},{"id":"2402.05421","title":"DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning","created":"2024-02-08","cited_by_count":6,"area":"offlinerl"},{"id":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2409.10589","title":"Offline Reinforcement Learning for Learning to Dispatch for Job Shop Scheduling","created":"2024-09-16","cited_by_count":6,"area":"offlinerl"},{"id":"2502.01784","title":"VILP: Imitation Learning with Latent Video Planning","created":"2025-02-03","cited_by_count":6,"area":"offlinerl"},{"id":"2301.13019","title":"Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies","created":"2023-01-30","cited_by_count":5,"area":"offlinerl"},{"id":"2309.16074","title":"Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning","created":"2023-09-28","cited_by_count":5,"area":"offlinerl"},{"id":"2406.10093","title":"BiKC: Keypose-Conditioned Consistency Policy for Bimanual Robotic Manipulation","created":"2024-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2503.08029","title":"Elastic Motion Policy: An Adaptive Dynamical System for Robust and Efficient One-Shot Imitation Learning","created":"2025-03-11","cited_by_count":5,"area":"offlinerl"},{"id":"2503.14259","title":"Quantization-Free Autoregressive Action Transformer","created":"2025-03-18","cited_by_count":5,"area":"offlinerl"},{"id":"2302.02607","title":"Target-based Surrogates for Stochastic Optimization","created":"2023-02-06","cited_by_count":4,"area":"offlinerl"},{"id":"2305.01400","title":"Get Back Here: Robust Imitation by Return-to-Distribution Planning","created":"2023-05-02","cited_by_count":4,"area":"offlinerl"},{"id":"2306.15228","title":"IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisors","created":"2023-06-27","cited_by_count":4,"area":"offlinerl"},{"id":"2401.04572","title":"Robust Imitation Learning for Automated Game Testing","created":"2024-01-09","cited_by_count":4,"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":"2410.07933","title":"Offline Hierarchical Reinforcement Learning via Inverse Optimization","created":"2024-10-10","cited_by_count":4,"area":"offlinerl"},{"id":"2506.00098","title":"Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey","created":"2025-05-30","cited_by_count":4,"area":"offlinerl"},{"id":"2509.19460","title":"Self-evolved Imitation Learning in Simulated World","created":"2025-09-23","cited_by_count":4,"area":"offlinerl"},{"id":"2512.16861","title":"ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learning","created":"2025-12-18","cited_by_count":4,"area":"offlinerl"},{"id":"2210.12272","title":"Implicit Offline Reinforcement Learning via Supervised Learning","created":"2022-10-21","cited_by_count":3,"area":"offlinerl"},{"id":"2303.01440","title":"Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations","created":"2023-03-02","cited_by_count":3,"area":"offlinerl"},{"id":"2311.09350","title":"Generalizable Imitation Learning Through Pre-Trained Representations","created":"2023-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2404.16399","title":"Offline Reinforcement Learning with Behavioral Supervisor Tuning","created":"2024-04-25","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":"2502.03698","title":"How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies","created":"2025-02-06","cited_by_count":3,"area":"offlinerl"},{"id":"2502.07645","title":"From Action Labels to Sets: Rethinking Action Supervision for Imitation Learning from Corrective Feedback","created":"2025-02-11","cited_by_count":3,"area":"offlinerl"},{"id":"2505.10760","title":"Counterfactual Behavior Cloning: Offline Imitation Learning from Imperfect Human Demonstrations","created":"2025-05-16","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":"2512.09101","title":"Masked Generative Policy for Robotic Control","created":"2025-12-09","cited_by_count":3,"area":"offlinerl"},{"id":"2601.21718","title":"When Does Predictive Inverse Dynamics Outperform Behavior Cloning?","created":"2026-01-29","cited_by_count":3,"area":"offlinerl"},{"id":"2602.17832","title":"MePoly: Max Entropy Polynomial Policy Optimization","created":"2026-02-19","cited_by_count":3,"area":"offlinerl"},{"id":"2605.12236","title":"TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning","created":"2026-05-12","cited_by_count":3,"area":"offlinerl"},{"id":"2301.12264","title":"Controlling Steering with Energy-Based Models","created":"2023-01-28","cited_by_count":2,"area":"offlinerl"},{"id":"2410.15714","title":"Offline reinforcement learning for job-shop scheduling problems","created":"2024-10-21","cited_by_count":2,"area":"offlinerl"},{"id":"2506.11262","title":"Demonstration Sidetracks: Categorizing Systematic Non-Optimality in Human Demonstrations","created":"2025-06-12","cited_by_count":2,"area":"offlinerl"},{"id":"2506.21057","title":"Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions","created":"2025-06-26","cited_by_count":2,"area":"offlinerl"},{"id":"2510.09487","title":"Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning","created":"2025-10-10","cited_by_count":2,"area":"offlinerl"},{"id":"2603.26720","title":"SutureFormer: Learning Surgical Trajectories via Goal-conditioned Offline RL in Pixel Space","created":"2026-03-19","cited_by_count":2,"area":"offlinerl"},{"id":"2201.03834","title":"STIR$^2$: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks","created":"2022-01-11","cited_by_count":1,"area":"offlinerl"},{"id":"2203.03432","title":"Learning Solution Manifolds for Control Problems via Energy Minimization","created":"2022-03-07","cited_by_count":1,"area":"offlinerl"}],"next_cursor":"100"}