{"total":79,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185,"area":"offlinerl"},{"id":"2010.12083","title":"Language-Conditioned Imitation Learning for Robot Manipulation Tasks","created":"2020-10-22","cited_by_count":136,"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":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103,"area":"offlinerl"},{"id":"1912.00177","title":"Urban Driving with Conditional Imitation Learning","created":"2019-11-30","cited_by_count":86,"area":"offlinerl"},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58,"area":"offlinerl"},{"id":"2205.11790","title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","created":"2022-05-24","cited_by_count":50,"area":"offlinerl"},{"id":"1903.00640","title":"Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safety","created":"2019-03-02","cited_by_count":49,"area":"offlinerl"},{"id":"2312.02976","title":"SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World","created":"2023-12-05","cited_by_count":48,"area":"offlinerl"},{"id":"2210.13435","title":"Dichotomy of Control: Separating What You Can Control from What You Cannot","created":"2022-10-24","cited_by_count":47,"area":"offlinerl"},{"id":"2102.09161","title":"On the Sample Complexity of Stability Constrained Imitation Learning","created":"2021-02-18","cited_by_count":38,"area":"offlinerl"},{"id":"2105.09371","title":"VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation","created":"2021-05-19","cited_by_count":31,"area":"offlinerl"},{"id":"2212.08244","title":"Offline Reinforcement Learning for Visual Navigation","created":"2022-12-16","cited_by_count":29,"area":"offlinerl"},{"id":"2103.05910","title":"Learning from Imperfect Demonstrations from Agents with Varying Dynamics","created":"2021-03-10","cited_by_count":27,"area":"offlinerl"},{"id":"2106.06452","title":"Keyframe-Focused Visual Imitation Learning","created":"2021-06-11","cited_by_count":25,"area":"offlinerl"},{"id":"1912.12204","title":"Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Data","created":"2019-12-24","cited_by_count":24,"area":"offlinerl"},{"id":"2111.11097","title":"UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning","created":"2021-11-22","cited_by_count":23,"area":"offlinerl"},{"id":"2212.00186","title":"Multi-Task Imitation Learning for Linear Dynamical Systems","created":"2022-12-01","cited_by_count":23,"area":"offlinerl"},{"id":"2203.09749","title":"Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation","created":"2022-03-18","cited_by_count":22,"area":"offlinerl"},{"id":"2205.14812","title":"TaSIL: Taylor Series Imitation Learning","created":"2022-05-30","cited_by_count":21,"area":"offlinerl"},{"id":"1905.02780","title":"Uncertainty-Aware Data Aggregation for Deep Imitation Learning","created":"2019-05-07","cited_by_count":20,"area":"offlinerl"},{"id":"2110.14118","title":"Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning","created":"2021-10-27","cited_by_count":17,"area":"offlinerl"},{"id":"2406.16087","title":"Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy","created":"2024-06-23","cited_by_count":16,"area":"offlinerl"},{"id":"2004.00981","title":"Benchmarking End-to-End Behavioural Cloning on Video Games","created":"2020-04-02","cited_by_count":15,"area":"offlinerl"},{"id":"2009.14509","title":"Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning","created":"2020-09-30","cited_by_count":14,"area":"offlinerl"},{"id":"2207.09705","title":"Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction","created":"2022-07-20","cited_by_count":14,"area":"offlinerl"},{"id":"2309.09408","title":"Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstration","created":"2023-09-18","cited_by_count":14,"area":"offlinerl"},{"id":"2404.05249","title":"SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems","created":"2024-04-08","cited_by_count":14,"area":"offlinerl"},{"id":"1909.12971","title":"Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation","created":"2019-09-27","cited_by_count":13,"area":"offlinerl"},{"id":"2201.01448","title":"Conditional Imitation Learning for Multi-Agent Games","created":"2022-01-05","cited_by_count":13,"area":"offlinerl"},{"id":"2309.01448","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","created":"2023-09-04","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":"2011.00509","title":"PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving","created":"2020-11-01","cited_by_count":11,"area":"offlinerl"},{"id":"1904.08377","title":"Gaze Training by Modulated Dropout Improves Imitation Learning","created":"2019-04-17","cited_by_count":10,"area":"offlinerl"},{"id":"1905.06002","title":"Simitate: A Hybrid Imitation Learning Benchmark","created":"2019-05-15","cited_by_count":10,"area":"offlinerl"},{"id":"2212.11365","title":"End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functions","created":"2022-12-21","cited_by_count":10,"area":"offlinerl"},{"id":"2301.00051","title":"Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks","created":"2022-12-30","cited_by_count":10,"area":"offlinerl"},{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"area":"offlinerl"},{"id":"2008.12969","title":"Driving Through Ghosts: Behavioral Cloning with False Positives","created":"2020-08-29","cited_by_count":8,"area":"offlinerl"},{"id":"2010.10393","title":"Imitation Learning of Hierarchical Driving Model: from Continuous Intention to Continuous Trajectory","created":"2020-10-20","cited_by_count":8,"area":"offlinerl"},{"id":"2410.03408","title":"Predictive Coding for Decision Transformer","created":"2024-10-04","cited_by_count":6,"area":"offlinerl"},{"id":"1808.04503","title":"Shared Multi-Task Imitation Learning for Indoor Self-Navigation","created":"2018-08-14","cited_by_count":5,"area":"offlinerl"},{"id":"2008.13193","title":"Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator","created":"2020-08-30","cited_by_count":5,"area":"offlinerl"},{"id":"1909.00895","title":"Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data","created":"2019-09-03","cited_by_count":4,"area":"offlinerl"},{"id":"2202.10124","title":"Multi-Task Conditional Imitation Learning for Autonomous Navigation at Crowded Intersections","created":"2022-02-21","cited_by_count":4,"area":"offlinerl"},{"id":"2410.15910","title":"Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning","created":"2024-10-21","cited_by_count":4,"area":"offlinerl"},{"id":"2112.08932","title":"Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning","created":"2021-12-16","cited_by_count":3,"area":"offlinerl"},{"id":"2211.06839","title":"Out-of-Dynamics Imitation Learning from Multimodal Demonstrations","created":"2022-11-13","cited_by_count":3,"area":"offlinerl"},{"id":"2410.03847","title":"Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping","created":"2024-10-04","cited_by_count":3,"area":"offlinerl"},{"id":"2008.01913","title":"Generalization Guarantees for Imitation Learning","created":"2020-08-05","cited_by_count":2,"area":"offlinerl"},{"id":"2301.12264","title":"Controlling Steering with Energy-Based Models","created":"2023-01-28","cited_by_count":2,"area":"offlinerl"},{"id":"2409.17605","title":"Good Data Is All Imitation Learning Needs","created":"2024-09-26","cited_by_count":2,"area":"offlinerl"},{"id":"2507.01161","title":"Imitation Learning for Satellite Attitude Control under Unknown Perturbations","created":"2025-07-01","cited_by_count":2,"area":"offlinerl"},{"id":"2301.07182","title":"Genetic Imitation Learning by Reward Extrapolation","created":"2023-01-03","cited_by_count":1,"area":"offlinerl"},{"id":"2304.02480","title":"Quantum Imitation Learning","created":"2023-04-04","cited_by_count":1,"area":"offlinerl"},{"id":"2309.07832","title":"VAPOR: Legged Robot Navigation in Outdoor Vegetation Using Offline Reinforcement Learning","created":"2023-09-14","cited_by_count":1,"area":"offlinerl"},{"id":"2311.17693","title":"Toward a Surgeon-in-the-Loop Ophthalmic Robotic Apprentice using Reinforcement and Imitation Learning","created":"2023-11-29","cited_by_count":1,"area":"offlinerl"},{"id":"2409.07218","title":"Behavioral Cloning Models Reality Check for Autonomous Driving","created":"2024-09-11","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":"2508.03129","title":"Safety-Aware Imitation Learning via MPC-Guided Disturbance Injection","created":"2025-08-05","cited_by_count":1,"area":"offlinerl"},{"id":"2509.13956","title":"SEG-Parking: Towards Safe, Efficient, and Generalizable Autonomous Parking via End-to-End Offline Reinforcement Learning","created":"2025-09-17","cited_by_count":1,"area":"offlinerl"},{"id":"2511.05158","title":"Follow-Me in Micro-Mobility with End-to-End Imitation Learning","created":"2025-11-07","cited_by_count":1,"area":"offlinerl"},{"id":"2512.17899","title":"Distributionally Robust Imitation Learning: Layered Control Architecture for Certifiable Autonomy","created":"2025-12-19","cited_by_count":1,"area":"offlinerl"},{"id":"1909.09721","title":"Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation","created":"2019-09-20","cited_by_count":0,"area":"offlinerl"},{"id":"2002.01059","title":"Preventing Imitation Learning with Adversarial Policy Ensembles","created":"2020-01-31","cited_by_count":0,"area":"offlinerl"},{"id":"2107.01407","title":"Optimality Inductive Biases and Agnostic Guidelines for Offline Reinforcement Learning","created":"2021-07-03","cited_by_count":0,"area":"offlinerl"},{"id":"2303.17010","title":"Specification-Guided Data Aggregation for Semantically Aware Imitation Learning","created":"2023-03-29","cited_by_count":0,"area":"offlinerl"},{"id":"2309.06658","title":"Dissipative Imitation Learning for Discrete Dynamic Output Feedback Control with Sparse Data Sets","created":"2023-09-13","cited_by_count":0,"area":"offlinerl"},{"id":"2310.00489","title":"Interpretable Imitation Learning with Dynamic Causal Relations","created":"2023-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2410.12238","title":"Off-dynamics Conditional Diffusion Planners","created":"2024-10-16","cited_by_count":0,"area":"offlinerl"},{"id":"2412.02931","title":"Inverse Delayed Reinforcement Learning","created":"2024-12-04","cited_by_count":0,"area":"offlinerl"},{"id":"2504.14709","title":"Exposing the Copycat Problem of Imitation-based Planner: A Novel Closed-Loop Simulator, Causal Benchmark and Joint IL-RL Baseline","created":"2025-04-20","cited_by_count":0,"area":"offlinerl"},{"id":"2509.02458","title":"Generative Sequential Notification Optimization via Multi-Objective Decision Transformers","created":"2025-09-02","cited_by_count":0,"area":"offlinerl"},{"id":"2601.00452","title":"Imitation from Observations with Trajectory-Level Generative Embeddings","created":"2026-01-01","cited_by_count":0,"area":"offlinerl"},{"id":"2604.22724","title":"GCImOpt: Learning efficient goal-conditioned policies by imitating optimal trajectories","created":"2026-04-24","cited_by_count":0,"area":"offlinerl"},{"id":"2609.05783","title":"Closed-Loop Evaluation of Bird's-Eye-View Maps from Cross-View Transformers as Inputs to Behavior-Cloning Policies","created":"2026-09-05","cited_by_count":0,"area":"offlinerl"},{"id":"2609.38407","title":"Disagreement-Regularized Imitation Learning for Image-Based Continuous Control with Gaussian and Beta Policies","created":"2026-09-29","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}