{"total":52,"rows":[{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492,"area":"offlinerl"},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459,"area":"offlinerl"},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452,"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":"1905.12888","title":"Imitation Learning as $f$-Divergence Minimization","created":"2019-05-30","cited_by_count":123,"area":"offlinerl"},{"id":"1910.12179","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","created":"2019-10-27","cited_by_count":91,"area":"offlinerl"},{"id":"1906.08113","title":"Wasserstein Adversarial Imitation Learning","created":"2019-06-19","cited_by_count":60,"area":"offlinerl"},{"id":"1907.13220","title":"Multi-Agent Adversarial Inverse Reinforcement Learning","created":"2019-07-30","cited_by_count":60,"area":"offlinerl"},{"id":"2310.15145","title":"Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning","created":"2023-10-23","cited_by_count":54,"area":null},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53,"area":null},{"id":"2006.06412","title":"Modeling Human Driving Behavior through Generative Adversarial Imitation Learning","created":"2020-06-10","cited_by_count":45,"area":"offlinerl"},{"id":"2308.02585","title":"PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback","created":"2023-08-03","cited_by_count":40,"area":"alignment"},{"id":"2011.06719","title":"Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulation","created":"2020-11-13","cited_by_count":38,"area":"offlinerl"},{"id":"1809.02064","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","created":"2018-09-06","cited_by_count":36,"area":"offlinerl"},{"id":"2502.19908","title":"CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-scale Reinforcement Learning in Autonomous Driving","created":"2025-02-27","cited_by_count":34,"area":"driving"},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2209.10974","title":"Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning","created":"2022-09-22","cited_by_count":16,"area":"offlinerl"},{"id":"2301.12130","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2006.16785","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning","created":"2020-06-28","cited_by_count":15,"area":"offlinerl"},{"id":"2405.02181","title":"Imitation Learning in Discounted Linear MDPs without exploration assumptions","created":"2024-05-03","cited_by_count":15,"area":"offlinerl"},{"id":"2104.09469","title":"Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior","created":"2021-04-19","cited_by_count":14,"area":null},{"id":"2410.18065","title":"SPIRE: Synergistic Planning, Imitation, and Reinforcement Learning for Long-Horizon Manipulation","created":"2024-10-23","cited_by_count":11,"area":"offlinerl"},{"id":"2112.14004","title":"Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations","created":"2021-12-28","cited_by_count":10,"area":"offlinerl"},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"1910.03157","title":"Model-based Behavioral Cloning with Future Image Similarity Learning","created":"2019-10-08","cited_by_count":8,"area":"offlinerl"},{"id":"2111.03474","title":"Supervised Advantage Actor-Critic for Recommender Systems","created":"2021-11-05","cited_by_count":8,"area":null},{"id":"2303.02073","title":"How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement","created":"2023-03-03","cited_by_count":8,"area":"offlinerl"},{"id":"2509.22925","title":"Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings","created":"2025-09-26","cited_by_count":6,"area":"diffusion"},{"id":"2012.13682","title":"POPO: Pessimistic Offline Policy Optimization","created":"2020-12-26","cited_by_count":5,"area":"offlinerl"},{"id":"2405.02299","title":"Deep Reinforcement Learning for Modelling Protein Complexes","created":"2024-03-11","cited_by_count":5,"area":null},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"id":"1911.07027","title":"On Value Discrepancy of Imitation Learning","created":"2019-11-16","cited_by_count":4,"area":"offlinerl"},{"id":"2101.01251","title":"Robust Maximum Entropy Behavior Cloning","created":"2021-01-04","cited_by_count":4,"area":"offlinerl"},{"id":"2401.11378","title":"Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance","created":"2024-01-21","cited_by_count":3,"area":"offlinerl"},{"id":"2104.06600","title":"GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback","created":"2021-04-14","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":"2402.07246","title":"Towards Generalized Inverse Reinforcement Learning","created":"2024-02-11","cited_by_count":2,"area":"offlinerl"},{"id":"2405.19183","title":"Conditional Latent ODEs for Motion Prediction in Autonomous Driving","created":"2024-05-29","cited_by_count":2,"area":"driving"},{"id":"2003.02638","title":"Metric-Based Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms","created":"2020-02-25","cited_by_count":1,"area":"offlinerl"},{"id":"2201.00039","title":"Stochastic convex optimization for provably efficient apprenticeship learning","created":"2021-12-31","cited_by_count":1,"area":"offlinerl"},{"id":"2201.05906","title":"Profitable Strategy Design by Using Deep Reinforcement Learning for Trades on Cryptocurrency Markets","created":"2022-01-15","cited_by_count":1,"area":null},{"id":"2305.03987","title":"Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization","created":"2023-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"1905.08513","title":"Stochastic Inverse Reinforcement Learning","created":"2019-05-21","cited_by_count":0,"area":"offlinerl"},{"id":"1912.08444","title":"Relational Mimic for Visual Adversarial Imitation Learning","created":"2019-12-18","cited_by_count":0,"area":"offlinerl"},{"id":"2103.16629","title":"Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustness","created":"2021-03-30","cited_by_count":0,"area":null},{"id":"2204.01975","title":"GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning","created":"2022-04-05","cited_by_count":0,"area":null},{"id":"2208.10533","title":"Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics","created":"2022-08-22","cited_by_count":0,"area":null},{"id":"2209.13046","title":"Understanding Hindsight Goal Relabeling from a Divergence Minimization Perspective","created":"2022-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2405.15509","title":"Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces","created":"2024-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2501.06376","title":"Robustness in the Face of Partial Identifiability in Reward Learning","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2605.12000","title":"Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation","created":"2026-05-12","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}