{"total":133,"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":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492,"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":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288,"area":"offlinerl"},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279,"area":"offlinerl"},{"id":"1810.02890","title":"HG-DAgger: Interactive Imitation Learning with Human Experts","created":"2018-10-05","cited_by_count":266,"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":"1912.05032","title":"Imitation Learning via Off-Policy Distribution Matching","created":"2019-12-10","cited_by_count":183,"area":"offlinerl"},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162,"area":"offlinerl"},{"id":"2203.15041","title":"Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation","created":"2022-03-28","cited_by_count":127,"area":"offlinerl"},{"id":"1905.13566","title":"Recent Advances in Imitation Learning from Observation","created":"2019-05-30","cited_by_count":93,"area":"offlinerl"},{"id":"2004.04650","title":"State-Only Imitation Learning for Dexterous Manipulation","created":"2020-04-07","cited_by_count":91,"area":"offlinerl"},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89,"area":"offlinerl"},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"1912.00177","title":"Urban Driving with Conditional Imitation Learning","created":"2019-11-30","cited_by_count":86,"area":"offlinerl"},{"id":"2103.03236","title":"Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap","created":"2021-03-04","cited_by_count":81,"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":"2010.14876","title":"Fighting Copycat Agents in Behavioral Cloning from Observation Histories","created":"2020-10-28","cited_by_count":71,"area":"offlinerl"},{"id":"2102.02872","title":"Feedback in Imitation Learning: The Three Regimes of Covariate Shift","created":"2021-02-04","cited_by_count":68,"area":"offlinerl"},{"id":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67,"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":"2110.13423","title":"Towards More Generalizable One-shot Visual Imitation Learning","created":"2021-10-26","cited_by_count":49,"area":"offlinerl"},{"id":"1910.04417","title":"Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement","created":"2019-10-10","cited_by_count":46,"area":"offlinerl"},{"id":"1905.06750","title":"Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation","created":"2019-05-16","cited_by_count":42,"area":"offlinerl"},{"id":"2105.10037","title":"Cross-domain Imitation from Observations","created":"2021-05-20","cited_by_count":42,"area":"offlinerl"},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"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":"2310.12972","title":"CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning","created":"2023-10-19","cited_by_count":29,"area":"offlinerl"},{"id":"1905.11108","title":"SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards","created":"2019-05-27","cited_by_count":28,"area":"offlinerl"},{"id":"1810.10593","title":"Inverse reinforcement learning for video games","created":"2018-10-24","cited_by_count":26,"area":"offlinerl"},{"id":"2503.09722","title":"The Pitfalls of Imitation Learning when Actions are Continuous","created":"2025-03-12","cited_by_count":26,"area":"offlinerl"},{"id":"2106.06452","title":"Keyframe-Focused Visual Imitation Learning","created":"2021-06-11","cited_by_count":25,"area":"offlinerl"},{"id":"2211.00194","title":"SEIL: Simulation-augmented Equivariant Imitation Learning","created":"2022-10-31","cited_by_count":23,"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":"2303.00638","title":"MEGA-DAgger: Imitation Learning with Multiple Imperfect Experts","created":"2023-03-01","cited_by_count":18,"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":"2309.10175","title":"One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers","created":"2023-09-18","cited_by_count":17,"area":"offlinerl"},{"id":"1905.12310","title":"Adversarial Imitation Learning from Incomplete Demonstrations","created":"2019-05-29","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":"2109.04307","title":"OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching","created":"2021-09-09","cited_by_count":15,"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":"1909.06953","title":"Off-road Autonomous Vehicles Traversability Analysis and Trajectory Planning Based on Deep Inverse Reinforcement Learning","created":"2019-09-16","cited_by_count":13,"area":"offlinerl"},{"id":"2211.00863","title":"Behavior Prior Representation learning for Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":12,"area":"offlinerl"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2309.16973","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","created":"2023-09-29","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":"1803.01129","title":"OIL: Observational Imitation Learning","created":"2018-03-03","cited_by_count":11,"area":"offlinerl"},{"id":"2010.04767","title":"Robust Behavioral Cloning for Autonomous Vehicles using End-to-End Imitation Learning","created":"2020-10-09","cited_by_count":11,"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":"2103.13887","title":"Adversarial Imitation Learning with Trajectorial Augmentation and Correction","created":"2021-03-25","cited_by_count":11,"area":"offlinerl"},{"id":"2109.09910","title":"Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC","created":"2021-09-21","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":"2011.13467","title":"Episodic Self-Imitation Learning with Hindsight","created":"2020-11-26","cited_by_count":10,"area":"offlinerl"},{"id":"2204.03195","title":"3D Perception based Imitation Learning under Limited Demonstration for Laparoscope Control in Robotic Surgery","created":"2022-04-07","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":"2310.18247","title":"Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning","created":"2023-10-27","cited_by_count":10,"area":"offlinerl"},{"id":"2007.11646","title":"Understanding Multi-Modal Perception Using Behavioral Cloning for Peg-In-a-Hole Insertion Tasks","created":"2020-07-22","cited_by_count":9,"area":"offlinerl"},{"id":"2212.04280","title":"Model-based trajectory stitching for improved behavioural cloning and its applications","created":"2022-12-08","cited_by_count":9,"area":"offlinerl"},{"id":"1910.03157","title":"Model-based Behavioral Cloning with Future Image Similarity Learning","created":"2019-10-08","cited_by_count":8,"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":"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":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"1810.07225","title":"Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories","created":"2018-10-16","cited_by_count":7,"area":"offlinerl"},{"id":"1907.02140","title":"Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model","created":"2019-07-03","cited_by_count":7,"area":"offlinerl"},{"id":"1909.11468","title":"Independent Generative Adversarial Self-Imitation Learning in Cooperative Multiagent Systems","created":"2019-09-25","cited_by_count":7,"area":"offlinerl"},{"id":"2004.08051","title":"Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning","created":"2020-04-17","cited_by_count":6,"area":"offlinerl"},{"id":"2010.08353","title":"On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration","created":"2020-10-16","cited_by_count":6,"area":"offlinerl"},{"id":"2103.12694","title":"Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks","created":"2021-03-23","cited_by_count":6,"area":"offlinerl"},{"id":"2103.13623","title":"Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies","created":"2021-03-25","cited_by_count":6,"area":"offlinerl"},{"id":"2411.15131","title":"WildLMa: Long Horizon Loco-Manipulation in the Wild","created":"2024-11-22","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":"1812.05841","title":"Imitation Learning for End to End Vehicle Longitudinal Control with Forward Camera","created":"2018-12-14","cited_by_count":5,"area":"offlinerl"},{"id":"2011.09586","title":"SAFARI: Safe and Active Robot Imitation Learning with Imagination","created":"2020-11-18","cited_by_count":5,"area":"offlinerl"},{"id":"2104.01390","title":"No Need for Interactions: Robust Model-Based Imitation Learning using Neural ODE","created":"2021-04-03","cited_by_count":5,"area":"offlinerl"},{"id":"2205.11448","title":"Data augmentation for efficient learning from parametric experts","created":"2022-05-23","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":"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":"1911.07027","title":"On Value Discrepancy of Imitation Learning","created":"2019-11-16","cited_by_count":4,"area":"offlinerl"},{"id":"2110.14464","title":"Learning from demonstrations with SACR2: Soft Actor-Critic with Reward Relabeling","created":"2021-10-27","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":"2305.01400","title":"Get Back Here: Robust Imitation by Return-to-Distribution Planning","created":"2023-05-02","cited_by_count":4,"area":"offlinerl"},{"id":"2307.15980","title":"Initial State Interventions for Deconfounded Imitation Learning","created":"2023-07-29","cited_by_count":4,"area":"offlinerl"},{"id":"2401.04572","title":"Robust Imitation Learning for Automated Game Testing","created":"2024-01-09","cited_by_count":4,"area":"offlinerl"},{"id":"2409.12001","title":"Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning","created":"2024-09-18","cited_by_count":4,"area":"offlinerl"},{"id":"2410.06151","title":"Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity","created":"2024-10-08","cited_by_count":4,"area":"offlinerl"},{"id":"2411.06965","title":"Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration","created":"2024-11-11","cited_by_count":4,"area":"offlinerl"},{"id":"2101.01052","title":"Imitation Learning for High Precision Peg-in-Hole Tasks","created":"2020-12-26","cited_by_count":3,"area":"offlinerl"},{"id":"2202.05500","title":"Multi-Modal Fusion for Sensorimotor Coordination in Steering Angle Prediction","created":"2022-02-11","cited_by_count":3,"area":"offlinerl"},{"id":"2303.01440","title":"Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations","created":"2023-03-02","cited_by_count":3,"area":"offlinerl"},{"id":"2007.05740","title":"Enhanced Behavioral Cloning Based self-driving Car Using Transfer Learning","created":"2020-07-11","cited_by_count":2,"area":"offlinerl"},{"id":"2012.05339","title":"Neural Rate Control for Video Encoding using Imitation Learning","created":"2020-12-09","cited_by_count":2,"area":"offlinerl"},{"id":"2210.10127","title":"Output Feedback Tube MPC-Guided Data Augmentation for Robust, Efficient Sensorimotor Policy Learning","created":"2022-10-18","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":"2401.01425","title":"SwapTransformer: highway overtaking tactical planner model via imitation learning on OSHA dataset","created":"2024-01-02","cited_by_count":2,"area":"offlinerl"},{"id":"2411.17458","title":"Spatially Visual Perception for End-to-End Robotic Learning","created":"2024-11-26","cited_by_count":2,"area":"offlinerl"},{"id":"2412.07057","title":"Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning","created":"2024-12-09","cited_by_count":2,"area":"offlinerl"},{"id":"2503.07737","title":"A Simple Approach to Constraint-Aware Imitation Learning with Application to Autonomous Racing","created":"2025-03-10","cited_by_count":2,"area":"offlinerl"},{"id":"2508.18397","title":"Mining the Long Tail: A Comparative Study of Data-Centric Criticality Metrics for Robust Offline Reinforcement Learning in Autonomous Motion Planning","created":"2025-08-25","cited_by_count":2,"area":"offlinerl"}],"next_cursor":"100"}