{"total":84,"rows":[{"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":"2212.03363","title":"Few-Shot Preference Learning for Human-in-the-Loop RL","created":"2022-12-06","cited_by_count":87,"area":null},{"id":"2306.02437","title":"Data Quality in Imitation Learning","created":"2023-06-04","cited_by_count":75,"area":"offlinerl"},{"id":"2202.01288","title":"Imitation Learning by Estimating Expertise of Demonstrators","created":"2022-02-02","cited_by_count":50,"area":"offlinerl"},{"id":"2110.14754","title":"Confidence-Aware Imitation Learning from Demonstrations with Varying Optimality","created":"2021-10-27","cited_by_count":44,"area":"offlinerl"},{"id":"2110.00284","title":"Learning Reward Functions from Scale Feedback","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2210.08073","title":"Eliciting Compatible Demonstrations for Multi-Human Imitation Learning","created":"2022-10-14","cited_by_count":23,"area":"offlinerl"},{"id":"2301.04741","title":"Efficient Preference-Based Reinforcement Learning Using Learned Dynamics Models","created":"2023-01-11","cited_by_count":21,"area":null},{"id":"2311.02013","title":"SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning","created":"2023-11-03","cited_by_count":21,"area":"offlinerl"},{"id":"2211.06519","title":"The Expertise Problem: Learning from Specialized Feedback","created":"2022-11-12","cited_by_count":20,"area":"alignment"},{"id":"2511.07416","title":"Robot Learning from a Physical World Model","created":"2025-11-10","cited_by_count":20,"area":"wm"},{"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":"2411.13451","title":"AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations","created":"2024-11-20","cited_by_count":19,"area":"mllm"},{"id":"2202.03481","title":"A Ranking Game for Imitation Learning","created":"2022-02-07","cited_by_count":18,"area":"offlinerl"},{"id":"2206.09670","title":"Benchmarking Constraint Inference in Inverse Reinforcement Learning","created":"2022-06-20","cited_by_count":18,"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":"2209.11908","title":"Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations","created":"2022-09-24","cited_by_count":14,"area":"offlinerl"},{"id":"2407.15403","title":"Offline Imitation Learning Through Graph Search and Retrieval","created":"2024-07-22","cited_by_count":14,"area":"offlinerl"},{"id":"2309.03315","title":"Robotic Table Tennis: A Case Study into a High Speed Learning System","created":"2023-09-06","cited_by_count":13,"area":null},{"id":"2402.01886","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators","created":"2024-02-02","cited_by_count":11,"area":"offlinerl"},{"id":"2206.04477","title":"Receding Horizon Inverse Reinforcement Learning","created":"2022-06-09","cited_by_count":10,"area":"offlinerl"},{"id":"2310.08549","title":"Cross-Episodic Curriculum for Transformer Agents","created":"2023-10-12","cited_by_count":10,"area":null},{"id":"2205.04195","title":"Disturbance-Injected Robust Imitation Learning with Task Achievement","created":"2022-05-09","cited_by_count":9,"area":"offlinerl"},{"id":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9,"area":"alignment"},{"id":"2510.09976","title":"Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models","created":"2025-10-11","cited_by_count":9,"area":"vla"},{"id":"2211.03393","title":"Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulation","created":"2022-11-07","cited_by_count":8,"area":"offlinerl"},{"id":"2402.13147","title":"SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning","created":"2024-02-20","cited_by_count":7,"area":"offlinerl"},{"id":"2502.15679","title":"BOSS: Benchmark for Observation Space Shift in Long-Horizon Task","created":"2025-02-21","cited_by_count":7,"area":"offlinerl"},{"id":"2507.19975","title":"A roadmap for AI in robotics","created":"2025-07-26","cited_by_count":7,"area":null},{"id":"2405.00746","title":"Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning","created":"2024-04-30","cited_by_count":6,"area":"deeprl"},{"id":"2202.02967","title":"Learning from Imperfect Demonstrations via Adversarial Confidence Transfer","created":"2022-02-07","cited_by_count":5,"area":"offlinerl"},{"id":"2306.11168","title":"Learning Models of Adversarial Agent Behavior under Partial Observability","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2310.14092","title":"Learning Reward for Physical Skills using Large Language Model","created":"2023-10-21","cited_by_count":5,"area":null},{"id":"2409.15528","title":"Learning Diverse Robot Striking Motions with Diffusion Models and Kinematically Constrained Gradient Guidance","created":"2024-09-23","cited_by_count":5,"area":"diffusion"},{"id":"2410.15994","title":"ARCADE: Scalable Demonstration Collection and Generation via Augmented Reality for Imitation Learning","created":"2024-10-21","cited_by_count":5,"area":"offlinerl"},{"id":"2101.07140","title":"Natural Language Specification of Reinforcement Learning Policies through Differentiable Decision Trees","created":"2021-01-18","cited_by_count":4,"area":null},{"id":"2212.01509","title":"Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward","created":"2022-12-03","cited_by_count":4,"area":null},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2401.17185","title":"Multi-Camera Asynchronous Ball Localization and Trajectory Prediction with Factor Graphs and Human Poses","created":"2024-01-30","cited_by_count":4,"area":null},{"id":"2405.03735","title":"Select to Perfect: Imitating desired behavior from large multi-agent data","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2101.00186","title":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","created":"2021-01-01","cited_by_count":3,"area":"offlinerl"},{"id":"2109.07788","title":"Marginal MAP Estimation for Inverse RL under Occlusion with Observer Noise","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2111.12867","title":"Back to Reality for Imitation Learning","created":"2021-11-25","cited_by_count":3,"area":"offlinerl"},{"id":"2212.02753","title":"Safe Inverse Reinforcement Learning via Control Barrier Function","created":"2022-12-06","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":"2409.15521","title":"CANDERE-COACH: Reinforcement Learning from Noisy Feedback","created":"2024-09-23","cited_by_count":3,"area":"offlinerl"},{"id":"2501.01367","title":"Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation","created":"2025-01-02","cited_by_count":3,"area":null},{"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":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2205.02959","title":"Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations","created":"2022-05-05","cited_by_count":2,"area":"offlinerl"},{"id":"2210.10469","title":"Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation","created":"2022-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2210.14428","title":"D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning","created":"2022-10-26","cited_by_count":2,"area":"offlinerl"},{"id":"2404.03382","title":"DIDA: Denoised Imitation Learning based on Domain Adaptation","created":"2024-04-04","cited_by_count":2,"area":"offlinerl"},{"id":"2407.06459","title":"How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots","created":"2024-07-08","cited_by_count":2,"area":"alignment"},{"id":"2504.05585","title":"TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning","created":"2025-04-08","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":"2107.02912","title":"Supervised Bayesian Specification Inference from Demonstrations","created":"2021-07-06","cited_by_count":1,"area":null},{"id":"2110.04347","title":"Towards Sample-efficient Apprenticeship Learning from Suboptimal Demonstration","created":"2021-10-08","cited_by_count":1,"area":"offlinerl"},{"id":"2202.07014","title":"Strategy Discovery and Mixture in Lifelong Learning from Heterogeneous Demonstration","created":"2022-02-14","cited_by_count":1,"area":"offlinerl"},{"id":"2307.05405","title":"Boosting Feedback Efficiency of Interactive Reinforcement Learning by Adaptive Learning from Scores","created":"2023-07-11","cited_by_count":1,"area":"alignment"},{"id":"2311.05084","title":"Signal Temporal Logic-Guided Apprenticeship Learning","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2402.18617","title":"ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games","created":"2024-02-28","cited_by_count":1,"area":"offlinerl"},{"id":"2409.19363","title":"Learning Strategy Representation for Imitation Learning in Multi-Agent Games","created":"2024-09-28","cited_by_count":1,"area":"offlinerl"},{"id":"2409.20258","title":"Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning","created":"2024-09-30","cited_by_count":1,"area":"deeprl"},{"id":"2412.11410","title":"MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning","created":"2024-12-16","cited_by_count":1,"area":"offlinerl"},{"id":"2505.21639","title":"Apprenticeship learning with prior beliefs using inverse optimization","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2510.06092","title":"Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2510.09096","title":"When a Robot is More Capable than a Human: Learning from Constrained Demonstrators","created":"2025-10-10","cited_by_count":1,"area":"offlinerl"},{"id":"2602.11018","title":"OSIL: Learning Offline Safe Imitation Policies with Safety Inferred from Non-preferred Trajectories","created":"2026-02-11","cited_by_count":1,"area":"offlinerl"},{"id":"2102.02454","title":"Exploring Beyond-Demonstrator via Meta Learning-Based Reward Extrapolation","created":"2021-02-04","cited_by_count":0,"area":"offlinerl"},{"id":"2310.08823","title":"Distance-rank Aware Sequential Reward Learning for Inverse Reinforcement Learning with Sub-optimal Demonstrations","created":"2023-10-13","cited_by_count":0,"area":"offlinerl"},{"id":"2403.13910","title":"Augmented Reality Demonstrations for Scalable Robot Imitation Learning","created":"2024-03-20","cited_by_count":0,"area":"offlinerl"},{"id":"2502.18447","title":"Supervised Reward Inference","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2504.14732","title":"Reinforcement Learning from Multi-level and Episodic Human Feedback","created":"2025-04-20","cited_by_count":0,"area":"alignment"},{"id":"2505.14820","title":"Imitation Learning via Focused Satisficing","created":"2025-05-20","cited_by_count":0,"area":"offlinerl"},{"id":"2507.06701","title":"Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement","created":"2025-07-09","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":"2511.20992","title":"Dataset Poisoning Attacks on Behavioral Cloning Policies","created":"2025-11-26","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":"2606.18537","title":"Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents","created":"2026-06-16","cited_by_count":0,"area":"offlinerl"},{"id":"2607.01225","title":"Language-Critique Imitation Learning from Suboptimal Demonstrations","created":"2026-07-01","cited_by_count":0,"area":"offlinerl"},{"id":"2609.13982","title":"Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Collaboration","created":"2026-09-12","cited_by_count":0,"area":"lr"},{"id":"2609.38225","title":"SynIL: Leveraging Synergy for Offline Imitation Learning from Imperfect Demonstration Datasets","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}