{"total":80,"rows":[{"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":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260,"area":"offlinerl"},{"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":"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":"2110.08176","title":"Collaborating with Humans without Human Data","created":"2021-10-15","cited_by_count":142,"area":"offlinerl"},{"id":"2310.07899","title":"RoboCLIP: One Demonstration is Enough to Learn Robot Policies","created":"2023-10-11","cited_by_count":134,"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":"2109.08273","title":"ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning","created":"2021-09-17","cited_by_count":108,"area":"offlinerl"},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73,"area":"offlinerl"},{"id":"1902.07742","title":"From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following","created":"2019-02-20","cited_by_count":67,"area":"offlinerl"},{"id":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53,"area":"offlinerl"},{"id":"2104.00053","title":"LazyDAgger: Reducing Context Switching in Interactive Imitation Learning","created":"2021-03-31","cited_by_count":51,"area":"offlinerl"},{"id":"2006.15061","title":"Intrinsic Reward Driven Imitation Learning via Generative Model","created":"2020-06-26","cited_by_count":35,"area":"offlinerl"},{"id":"2211.11972","title":"imitation: Clean Imitation Learning Implementations","created":"2022-11-22","cited_by_count":34,"area":"offlinerl"},{"id":"2111.02767","title":"RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning","created":"2021-11-04","cited_by_count":31,"area":"offlinerl"},{"id":"2204.10759","title":"The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models","created":"2022-04-22","cited_by_count":31,"area":"offlinerl"},{"id":"2402.05546","title":"Offline Actor-Critic Reinforcement Learning Scales to Large Models","created":"2024-02-08","cited_by_count":30,"area":"offlinerl"},{"id":"1810.10593","title":"Inverse reinforcement learning for video games","created":"2018-10-24","cited_by_count":26,"area":"offlinerl"},{"id":"1901.02161","title":"Risk-Aware Active Inverse Reinforcement Learning","created":"2019-01-08","cited_by_count":26,"area":"offlinerl"},{"id":"2106.00099","title":"Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs","created":"2021-05-31","cited_by_count":22,"area":"offlinerl"},{"id":"2409.01369","title":"Imitating Language via Scalable Inverse Reinforcement Learning","created":"2024-09-02","cited_by_count":21,"area":"offlinerl"},{"id":"2207.03395","title":"Unified Learning from Demonstrations, Corrections, and Preferences during Physical Human-Robot Interaction","created":"2022-07-07","cited_by_count":19,"area":"offlinerl"},{"id":"1909.12200","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","created":"2019-09-26","cited_by_count":18,"area":"offlinerl"},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2107.09251","title":"Offline Preference-Based Apprenticeship Learning","created":"2021-07-20","cited_by_count":17,"area":"offlinerl"},{"id":"2404.19456","title":"A Survey of Imitation Learning Methods, Environments and Metrics","created":"2024-04-30","cited_by_count":16,"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":"2402.03081","title":"Preference-Conditioned Language-Guided Abstraction","created":"2024-02-05","cited_by_count":12,"area":"offlinerl"},{"id":"2106.06499","title":"Policy Gradient Bayesian Robust Optimization for Imitation Learning","created":"2021-06-11","cited_by_count":11,"area":"offlinerl"},{"id":"2402.18759","title":"Learning with Language-Guided State Abstractions","created":"2024-02-28","cited_by_count":11,"area":"offlinerl"},{"id":"2008.00524","title":"Interactive Imitation Learning in State-Space","created":"2020-08-02","cited_by_count":10,"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":"2007.07812","title":"Inverse Reinforcement Learning from a Gradient-based Learner","created":"2020-07-15","cited_by_count":7,"area":"offlinerl"},{"id":"1907.03976","title":"Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations","created":"2019-07-09","cited_by_count":6,"area":"offlinerl"},{"id":"1909.03773","title":"Imitation Learning from Pixel-Level Demonstrations by HashReward","created":"2019-09-09","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":"2012.02527","title":"Demonstration-efficient Inverse Reinforcement Learning in Procedurally Generated Environments","created":"2020-12-04","cited_by_count":6,"area":"offlinerl"},{"id":"2104.07810","title":"Skeletal Feature Compensation for Imitation Learning with Embodiment Mismatch","created":"2021-04-15","cited_by_count":5,"area":"offlinerl"},{"id":"2111.04279","title":"Batch Reinforcement Learning from Crowds","created":"2021-11-08","cited_by_count":4,"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":"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":"2211.15339","title":"Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning","created":"2022-11-24","cited_by_count":3,"area":"offlinerl"},{"id":"2302.06271","title":"Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning","created":"2023-02-13","cited_by_count":3,"area":"offlinerl"},{"id":"2310.07143","title":"Imitation Learning from Purified Demonstrations","created":"2023-10-11","cited_by_count":3,"area":"offlinerl"},{"id":"2401.11378","title":"Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance","created":"2024-01-21","cited_by_count":3,"area":"offlinerl"},{"id":"2406.04913","title":"Online Adaptation for Enhancing Imitation Learning Policies","created":"2024-06-07","cited_by_count":3,"area":"offlinerl"},{"id":"2406.18450","title":"Preference Elicitation for Offline Reinforcement Learning","created":"2024-06-26","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":"2411.10268","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","created":"2024-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2501.02330","title":"SR-Reward: Taking The Path More Traveled","created":"2025-01-04","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":"2203.11197","title":"Teachable Reinforcement Learning via Advice Distillation","created":"2022-03-19","cited_by_count":2,"area":"offlinerl"},{"id":"2301.09770","title":"Language-guided Task Adaptation for Imitation Learning","created":"2023-01-24","cited_by_count":2,"area":"offlinerl"},{"id":"2404.07185","title":"Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery","created":"2024-04-10","cited_by_count":2,"area":"offlinerl"},{"id":"2503.15368","title":"Online Imitation Learning for Manipulation via Decaying Relative Correction through Teleoperation","created":"2025-03-19","cited_by_count":2,"area":"offlinerl"},{"id":"2508.01167","title":"T2S: Tokenized Skill Scaling for Lifelong Imitation Learning","created":"2025-08-02","cited_by_count":2,"area":"offlinerl"},{"id":"2509.03790","title":"What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?","created":"2025-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"2011.09264","title":"Inverse Reinforcement Learning via Matching of Optimality Profiles","created":"2020-11-18","cited_by_count":1,"area":"offlinerl"},{"id":"2104.01021","title":"Learning Online from Corrective Feedback: A Meta-Algorithm for Robotics","created":"2021-04-02","cited_by_count":1,"area":"offlinerl"},{"id":"2206.05827","title":"Case-Based Inverse Reinforcement Learning Using Temporal Coherence","created":"2022-06-12","cited_by_count":1,"area":"offlinerl"},{"id":"2301.07182","title":"Genetic Imitation Learning by Reward Extrapolation","created":"2023-01-03","cited_by_count":1,"area":"offlinerl"},{"id":"2411.08637","title":"Robot See, Robot Do: Imitation Reward for Noisy Financial Environments","created":"2024-11-13","cited_by_count":1,"area":"offlinerl"},{"id":"2506.20307","title":"Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration","created":"2025-06-25","cited_by_count":1,"area":"offlinerl"},{"id":"2309.03839","title":"Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning","created":"2023-09-07","cited_by_count":0,"area":"offlinerl"},{"id":"2502.20089","title":"RIZE: Adaptive Regularization for Imitation Learning","created":"2025-02-27","cited_by_count":0,"area":"offlinerl"},{"id":"2505.14820","title":"Imitation Learning via Focused Satisficing","created":"2025-05-20","cited_by_count":0,"area":"offlinerl"},{"id":"2507.08707","title":"SPLASH! Sample-efficient Preference-based inverse reinforcement learning for Long-horizon Adversarial tasks from Suboptimal Hierarchical demonstrations","created":"2025-07-11","cited_by_count":0,"area":"offlinerl"},{"id":"2508.15327","title":"Search-Based Credit Assignment for Offline Preference-Based Reinforcement Learning","created":"2025-08-21","cited_by_count":0,"area":"offlinerl"},{"id":"2509.15498","title":"Mental Accounts for Actions: EWA-Inspired Attention in Decision Transformers","created":"2025-09-19","cited_by_count":0,"area":"offlinerl"},{"id":"2509.26294","title":"Noise-Guided Transport for Imitation Learning","created":"2025-09-30","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":"2604.13175","title":"Pareto-Optimal Offline Reinforcement Learning via Smooth Tchebycheff Scalarization","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2605.30903","title":"Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach","created":"2026-05-29","cited_by_count":0,"area":"offlinerl"},{"id":"2607.01925","title":"SPLC: Social Preference Learning for Crowd Robot Navigation","created":"2026-07-02","cited_by_count":0,"area":"offlinerl"},{"id":"2607.19199","title":"Conservative Query and Adaptive Regularization for Offline RL Under Uncertainty Estimation","created":"2026-07-21","cited_by_count":0,"area":"offlinerl"},{"id":"2609.12014","title":"Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning","created":"2026-09-10","cited_by_count":0,"area":"offlinerl"},{"id":"2610.00758","title":"Scalable Multi-Task Inverse Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}