{"total":57,"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":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2302.00935","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","created":"2023-02-02","cited_by_count":104,"area":"offlinerl"},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29,"area":"offlinerl"},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24,"area":"offlinerl"},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2306.13085","title":"Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting","created":"2023-06-22","cited_by_count":22,"area":"offlinerl"},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21,"area":"offlinerl"},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2303.17156","title":"MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations","created":"2023-03-30","cited_by_count":18,"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":"2402.03807","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","created":"2024-02-06","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":"2306.14534","title":"CEIL: Generalized Contextual Imitation Learning","created":"2023-06-26","cited_by_count":13,"area":"offlinerl"},{"id":"2405.19909","title":"Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning","created":"2024-05-30","cited_by_count":13,"area":"offlinerl"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"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":"2306.13412","title":"CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning","created":"2023-06-23","cited_by_count":11,"area":"offlinerl"},{"id":"2402.01886","title":"Inverse Reinforcement Learning by Estimating Expertise of Demonstrators","created":"2024-02-02","cited_by_count":11,"area":"offlinerl"},{"id":"2301.11734","title":"Improving Behavioural Cloning with Positive Unlabeled Learning","created":"2023-01-27","cited_by_count":8,"area":"offlinerl"},{"id":"2406.12550","title":"Offline Imitation Learning with Model-based Reverse Augmentation","created":"2024-06-18","cited_by_count":8,"area":"offlinerl"},{"id":"2410.01954","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","created":"2024-10-02","cited_by_count":8,"area":"offlinerl"},{"id":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2310.04706","title":"Offline Imitation Learning with Variational Counterfactual Reasoning","created":"2023-10-07","cited_by_count":7,"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":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2306.07919","title":"Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations","created":"2023-06-13","cited_by_count":5,"area":"offlinerl"},{"id":"2410.03626","title":"Robust Offline Imitation Learning from Diverse Auxiliary Data","created":"2024-10-04","cited_by_count":5,"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":"2408.09125","title":"Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning","created":"2024-08-17","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":"2508.14383","title":"Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations","created":"2025-08-20","cited_by_count":3,"area":"offlinerl"},{"id":"2301.11687","title":"Theoretical Analysis of Offline Imitation With Supplementary Dataset","created":"2023-01-27","cited_by_count":2,"area":"offlinerl"},{"id":"2308.12573","title":"Conditional Kernel Imitation Learning for Continuous State Environments","created":"2023-08-24","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":"2412.20193","title":"Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker","created":"2024-12-28","cited_by_count":1,"area":"offlinerl"},{"id":"2503.22524","title":"Robust Offline Imitation Learning Through State-level Trajectory Stitching","created":"2025-03-28","cited_by_count":1,"area":"offlinerl"},{"id":"2602.10793","title":"Semi-Supervised Cross-Domain Imitation Learning","created":"2026-02-11","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":"2406.03324","title":"UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning","created":"2024-06-05","cited_by_count":0,"area":"offlinerl"},{"id":"2410.08307","title":"UNIQ: Offline Inverse Q-learning for Avoiding Undesirable Demonstrations","created":"2024-10-10","cited_by_count":0,"area":"offlinerl"},{"id":"2505.21182","title":"Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations","created":"2025-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2506.22008","title":"TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning","created":"2025-06-27","cited_by_count":0,"area":"offlinerl"},{"id":"2510.01479","title":"Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets","created":"2025-10-01","cited_by_count":0,"area":"offlinerl"},{"id":"2511.03616","title":"Going Beyond Expert Performance via Deep Implicit Imitation Reinforcement Learning","created":"2025-11-05","cited_by_count":0,"area":"offlinerl"},{"id":"2511.08136","title":"SafeMIL: Learning Offline Safe Imitation Policy from Non-Preferred Trajectories","created":"2025-11-11","cited_by_count":0,"area":"offlinerl"},{"id":"2601.05383","title":"Imitation Learning for Combinatorial Optimisation under Uncertainty","created":"2026-01-08","cited_by_count":0,"area":"offlinerl"},{"id":"2601.23010","title":"Automatic Constraint Policy Optimization based on Continuous Constraint Interpolation Framework for Offline Reinforcement Learning","created":"2026-01-30","cited_by_count":0,"area":"offlinerl"},{"id":"2605.25414","title":"How to Mitigate the Distribution Shift Problem in Robotics Control: A Robust and Adaptive Approach Based on Offline to Online Imitation Learning","created":"2026-05-25","cited_by_count":0,"area":"offlinerl"},{"id":"2606.20871","title":"Geometric Entropy: When Trajectory Diversity Helps and Hurts in Imitation Learning","created":"2026-06-18","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":"2607.17003","title":"Scalable Causal Imitation Learning","created":"2026-07-18","cited_by_count":0,"area":"offlinerl"},{"id":"2607.17760","title":"Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning","created":"2026-07-20","cited_by_count":0,"area":"offlinerl"},{"id":"2609.29000","title":"Learning from Mixed-Quality Deployment Experience for Robot Manipulation","created":"2026-09-24","cited_by_count":0,"area":"offlinerl"},{"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}