{"total":54,"rows":[{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206,"area":"offlinerl"},{"id":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158,"area":"offlinerl"},{"id":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142,"area":"offlinerl"},{"id":"2305.12821","title":"FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation","created":"2023-05-22","cited_by_count":133,"area":"offlinerl"},{"id":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115,"area":"offlinerl"},{"id":"2004.04650","title":"State-Only Imitation Learning for Dexterous Manipulation","created":"2020-04-07","cited_by_count":91,"area":"offlinerl"},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90,"area":"offlinerl"},{"id":"2204.12490","title":"From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation","created":"2022-04-26","cited_by_count":82,"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":"2305.16309","title":"Imitating Task and Motion Planning with Visuomotor Transformers","created":"2023-05-25","cited_by_count":66,"area":"offlinerl"},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"id":"2204.02320","title":"Learning Generalizable Dexterous Manipulation from Human Grasp Affordance","created":"2022-04-05","cited_by_count":51,"area":"offlinerl"},{"id":"2505.09723","title":"EnerVerse-AC: Envisioning Embodied Environments with Action Condition","created":"2025-05-14","cited_by_count":42,"area":"offlinerl"},{"id":"2402.14795","title":"CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation","created":"2024-02-22","cited_by_count":28,"area":"offlinerl"},{"id":"2203.08398","title":"COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks","created":"2022-03-16","cited_by_count":26,"area":"offlinerl"},{"id":"2106.09119","title":"Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL","created":"2021-06-16","cited_by_count":24,"area":"offlinerl"},{"id":"2307.15690","title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","created":"2023-07-28","cited_by_count":23,"area":"offlinerl"},{"id":"2405.06192","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","created":"2024-05-10","cited_by_count":18,"area":"offlinerl"},{"id":"2309.12716","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","created":"2023-09-22","cited_by_count":17,"area":"offlinerl"},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16,"area":"offlinerl"},{"id":"2306.00629","title":"Identifiability and Generalizability in Constrained Inverse Reinforcement Learning","created":"2023-06-01","cited_by_count":16,"area":"offlinerl"},{"id":"2006.16785","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","created":"2020-06-28","cited_by_count":15,"area":"offlinerl"},{"id":"2209.12093","title":"Learn what matters: cross-domain imitation learning with task-relevant embeddings","created":"2022-09-24","cited_by_count":14,"area":"offlinerl"},{"id":"2209.09991","title":"Optimizing Crop Management with Reinforcement Learning and Imitation Learning","created":"2022-09-20","cited_by_count":13,"area":"offlinerl"},{"id":"2411.16959","title":"RoCoDA: Counterfactual Data Augmentation for Data-Efficient Robot Learning from Demonstrations","created":"2024-11-25","cited_by_count":13,"area":"offlinerl"},{"id":"2311.08384","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","created":"2023-11-14","cited_by_count":11,"area":"offlinerl"},{"id":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","cited_by_count":9,"area":"offlinerl"},{"id":"2404.12530","title":"TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents","created":"2024-04-18","cited_by_count":7,"area":"offlinerl"},{"id":"2404.17684","title":"Generalize by Touching: Tactile Ensemble Skill Transfer for Robotic Furniture Assembly","created":"2024-04-26","cited_by_count":7,"area":"offlinerl"},{"id":"2008.07284","title":"Forward and inverse reinforcement learning sharing network weights and hyperparameters","created":"2020-08-17","cited_by_count":6,"area":"offlinerl"},{"id":"2012.01365","title":"DERAIL: Diagnostic Environments for Reward And Imitation Learning","created":"2020-12-02","cited_by_count":6,"area":"offlinerl"},{"id":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6,"area":"offlinerl"},{"id":"2401.07603","title":"Multi-task real-robot data with gaze attention for dual-arm fine manipulation","created":"2024-01-15","cited_by_count":5,"area":"offlinerl"},{"id":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2210.14972","title":"Environment Design for Inverse Reinforcement Learning","created":"2022-10-26","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":"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":"2507.22380","title":"Improving Generalization Ability of Robotic Imitation Learning by Resolving Causal Confusion in Observations","created":"2025-07-30","cited_by_count":4,"area":"offlinerl"},{"id":"2308.07741","title":"Real Robot Challenge 2022: Learning Dexterous Manipulation from Offline Data in the Real World","created":"2023-08-15","cited_by_count":3,"area":"offlinerl"},{"id":"2409.15521","title":"CANDERE-COACH: Reinforcement Learning from Noisy Feedback","created":"2024-09-23","cited_by_count":3,"area":"offlinerl"},{"id":"2505.11719","title":"Zero-Shot Visual Generalization in Robot Manipulation","created":"2025-05-16","cited_by_count":3,"area":"offlinerl"},{"id":"2203.11197","title":"Teachable Reinforcement Learning via Advice Distillation","created":"2022-03-19","cited_by_count":2,"area":"offlinerl"},{"id":"2204.07404","title":"Divide & Conquer Imitation Learning","created":"2022-04-15","cited_by_count":2,"area":"offlinerl"},{"id":"2503.12283","title":"Towards Optimal Offline Reinforcement Learning","created":"2025-03-15","cited_by_count":2,"area":"offlinerl"},{"id":"2509.12010","title":"Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids","created":"2025-09-15","cited_by_count":1,"area":"offlinerl"},{"id":"2204.07631","title":"Evaluating the Effectiveness of Corrective Demonstrations and a Low-Cost Sensor for Dexterous Manipulation","created":"2022-04-15","cited_by_count":0,"area":"offlinerl"},{"id":"2310.05712","title":"Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments","created":"2023-10-09","cited_by_count":0,"area":"offlinerl"},{"id":"2503.02738","title":"Variable-Friction In-Hand Manipulation for Arbitrary Objects via Diffusion-Based Imitation Learning","created":"2025-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2511.17595","title":"Boosting Reinforcement Learning in 3D Visuospatial Tasks Through Human-Informed Curriculum Design","created":"2025-11-17","cited_by_count":0,"area":"offlinerl"},{"id":"2605.09183","title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","created":"2026-05-09","cited_by_count":0,"area":"offlinerl"},{"id":"2605.23847","title":"Instrumentation for Imitation Learning: Enhancing Training Datasets for Clothes Hanger Insertion","created":"2026-05-22","cited_by_count":0,"area":"offlinerl"},{"id":"2608.24741","title":"One-Shot Learning from Demonstration of Contact-Rich Robotic Manipulation by Identifying Physical Interactions","created":"2026-08-25","cited_by_count":0,"area":"offlinerl"},{"id":"2609.01453","title":"Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds","created":"2026-09-01","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}