{"total":43,"rows":[{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288,"area":"offlinerl"},{"id":"2309.02473","title":"A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges","created":"2023-09-05","cited_by_count":148,"area":"offlinerl"},{"id":"1912.00177","title":"Urban Driving with Conditional Imitation Learning","created":"2019-11-30","cited_by_count":86,"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":"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":"1905.06750","title":"Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation","created":"2019-05-16","cited_by_count":42,"area":"offlinerl"},{"id":"2208.02225","title":"Sequence Model Imitation Learning with Unobserved Contexts","created":"2022-08-03","cited_by_count":34,"area":"offlinerl"},{"id":"2202.01312","title":"Causal Imitation Learning under Temporally Correlated Noise","created":"2022-02-02","cited_by_count":28,"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":"2602.15010","title":"BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames","created":"2026-02-16","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":"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":"2404.05249","title":"SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems","created":"2024-04-08","cited_by_count":14,"area":"offlinerl"},{"id":"2502.12465","title":"Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification","created":"2025-02-18","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":"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":"2210.11796","title":"Differentiable Constrained Imitation Learning for Robot Motion Planning and Control","created":"2022-10-21","cited_by_count":7,"area":"offlinerl"},{"id":"2306.00585","title":"Causal Imitability Under Context-Specific Independence Relations","created":"2023-06-01","cited_by_count":6,"area":"offlinerl"},{"id":"2106.09159","title":"Automatic Curricula via Expert Demonstrations","created":"2021-06-16","cited_by_count":5,"area":"offlinerl"},{"id":"2107.04485","title":"Adversarial Mixture Density Networks: Learning to Drive Safely from Collision Data","created":"2021-07-09","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":"2007.05740","title":"Enhanced Behavioral Cloning Based self-driving Car Using Transfer Learning","created":"2020-07-11","cited_by_count":2,"area":"offlinerl"},{"id":"2008.01913","title":"Generalization Guarantees for Imitation Learning","created":"2020-08-05","cited_by_count":2,"area":"offlinerl"},{"id":"2203.01696","title":"Fail-Safe Adversarial Generative Imitation Learning","created":"2022-03-03","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":"2503.03056","title":"A2Perf: Real-World Autonomous Agents Benchmark","created":"2025-03-04","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"},{"id":"2007.07443","title":"Deep PQR: Solving Inverse Reinforcement Learning using Anchor Actions","created":"2020-07-15","cited_by_count":1,"area":"offlinerl"},{"id":"2502.07656","title":"Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding","created":"2025-02-11","cited_by_count":1,"area":"offlinerl"},{"id":"2603.22527","title":"Learning Sidewalk Autopilot from Multi-Scale Imitation with Corrective Behavior Expansion","created":"2026-03-23","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":"2303.17010","title":"Specification-Guided Data Aggregation for Semantically Aware Imitation Learning","created":"2023-03-29","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":"2503.05997","title":"Learning to Drive by Imitating Surrounding Vehicles","created":"2025-03-08","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":"2507.17309","title":"Confounded Causal Imitation Learning with Instrumental Variables","created":"2025-07-23","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":"2605.24405","title":"Generative OOD-regularized Model-based Policy Optimization","created":"2026-05-23","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"}],"next_cursor":null}