{"total":54,"rows":[{"id":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193,"area":"offlinerl"},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"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":"2407.01812","title":"Equivariant Diffusion Policy","created":"2024-07-01","cited_by_count":66,"area":"diffusion"},{"id":"2205.03195","title":"Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation","created":"2022-05-06","cited_by_count":61,"area":null},{"id":"2102.06483","title":"Scalable Bayesian Inverse Reinforcement Learning","created":"2021-02-12","cited_by_count":56,"area":"offlinerl"},{"id":"2405.15624","title":"Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning","created":"2024-05-24","cited_by_count":27,"area":"alignment"},{"id":"2412.06782","title":"CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction","created":"2024-12-09","cited_by_count":27,"area":null},{"id":"2106.03207","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage","created":"2021-06-06","cited_by_count":26,"area":"offlinerl"},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2402.16075","title":"Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion","created":"2024-02-25","cited_by_count":21,"area":"diffusion"},{"id":"2302.04782","title":"CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning","created":"2023-02-09","cited_by_count":20,"area":"offlinerl"},{"id":"2310.06147","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","created":"2023-10-09","cited_by_count":20,"area":"alignment"},{"id":"2410.14250","title":"Vision-Language Navigation with Energy-Based Policy","created":"2024-10-18","cited_by_count":19,"area":null},{"id":"2207.00244","title":"Discriminator-Guided Model-Based Offline Imitation Learning","created":"2022-07-01","cited_by_count":17,"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":"2311.01489","title":"Invariant Causal Imitation Learning for Generalizable Policies","created":"2023-11-02","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":"2107.03851","title":"Imitation by Predicting Observations","created":"2021-07-08","cited_by_count":13,"area":"offlinerl"},{"id":"2306.14534","title":"CEIL: Generalized Contextual Imitation Learning","created":"2023-06-26","cited_by_count":13,"area":"offlinerl"},{"id":"2107.06317","title":"Inverse Contextual Bandits: Learning How Behavior Evolves over Time","created":"2021-07-13","cited_by_count":12,"area":null},{"id":"2403.12017","title":"Supervised Fine-Tuning as Inverse Reinforcement Learning","created":"2024-03-18","cited_by_count":12,"area":"alignment"},{"id":"2405.17476","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","created":"2024-05-24","cited_by_count":12,"area":"offlinerl"},{"id":"2106.04240","title":"The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation","created":"2021-06-08","cited_by_count":11,"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":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2503.03998","title":"Robotic Compliant Object Prying Using Diffusion Policy Guided by Vision and Force Observations","created":"2025-03-06","cited_by_count":10,"area":"diffusion"},{"id":"2310.07747","title":"Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples","created":"2023-10-11","cited_by_count":9,"area":"offlinerl"},{"id":"2311.01419","title":"C3DM: Constrained-Context Conditional Diffusion Models for Imitation Learning","created":"2023-11-02","cited_by_count":8,"area":"diffusion"},{"id":"2507.13158","title":"Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities","created":"2025-07-17","cited_by_count":7,"area":"alignment"},{"id":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2306.08232","title":"Curricular Subgoals for Inverse Reinforcement Learning","created":"2023-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2401.17500","title":"LeTO: Learning Constrained Visuomotor Policy with Differentiable Trajectory Optimization","created":"2024-01-30","cited_by_count":5,"area":null},{"id":"2102.13008","title":"Imitation Learning with Human Eye Gaze via Multi-Objective Prediction","created":"2021-02-25","cited_by_count":4,"area":"offlinerl"},{"id":"2110.02063","title":"A Critique of Strictly Batch Imitation Learning","created":"2021-10-05","cited_by_count":4,"area":"offlinerl"},{"id":"2208.04919","title":"Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience","created":"2022-08-09","cited_by_count":4,"area":"offlinerl"},{"id":"2407.10971","title":"Walking the Values in Bayesian Inverse Reinforcement Learning","created":"2024-07-15","cited_by_count":4,"area":"offlinerl"},{"id":"2310.19831","title":"Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning","created":"2023-10-28","cited_by_count":3,"area":null},{"id":"2402.04567","title":"OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences","created":"2024-02-07","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":"2511.13765","title":"PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning","created":"2025-11-14","cited_by_count":3,"area":"alignment"},{"id":"2308.12573","title":"Conditional Kernel Imitation Learning for Continuous State Environments","created":"2023-08-24","cited_by_count":2,"area":"offlinerl"},{"id":"2406.02450","title":"A Generalized Apprenticeship Learning Framework for Modeling Heterogeneous Student Pedagogical Strategies","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2505.20335","title":"Language Model Distillation: A Temporal Difference Imitation Learning Perspective","created":"2025-05-24","cited_by_count":2,"area":"offlinerl"},{"id":"2506.04716","title":"Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion","created":"2025-06-05","cited_by_count":2,"area":"diffusion"},{"id":"2602.20527","title":"A Generalized Apprenticeship Learning Framework for Capturing Evolving Student Pedagogical Strategies","created":"2026-02-24","cited_by_count":2,"area":"deeprl"},{"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":"2305.09070","title":"An Offline Time-aware Apprenticeship Learning Framework for Evolving Reward Functions","created":"2023-05-15","cited_by_count":1,"area":null},{"id":"2206.05521","title":"Model-based Offline Imitation Learning with Non-expert Data","created":"2022-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2409.12061","title":"Generalized Robot Learning Framework","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2604.00258","title":"Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.08475","title":"LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation","created":"2026-04-09","cited_by_count":0,"area":null}],"next_cursor":null}