{"total":72,"rows":[{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125,"area":"offlinerl"},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108,"area":null},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"id":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","cited_by_count":70,"area":"offlinerl"},{"id":"2301.01392","title":"Benchmarks and Algorithms for Offline Preference-Based Reward Learning","created":"2023-01-03","cited_by_count":56,"area":"alignment"},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53,"area":"offlinerl"},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2202.02433","title":"Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching","created":"2022-02-04","cited_by_count":43,"area":"offlinerl"},{"id":"2303.13971","title":"Optimal Transport for Offline Imitation Learning","created":"2023-03-24","cited_by_count":42,"area":"offlinerl"},{"id":"2110.14770","title":"TRAIL: Near-Optimal Imitation Learning with Suboptimal Data","created":"2021-10-27","cited_by_count":39,"area":"offlinerl"},{"id":"2103.12656","title":"Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification","created":"2021-03-23","cited_by_count":38,"area":null},{"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":"2012.06899","title":"Semi-supervised reward learning for offline reinforcement learning","created":"2020-12-12","cited_by_count":23,"area":"alignment"},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"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":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2205.06760","title":"Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning","created":"2022-05-13","cited_by_count":19,"area":null},{"id":"2303.17156","title":"MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations","created":"2023-03-30","cited_by_count":18,"area":"offlinerl"},{"id":"2107.09251","title":"Offline Preference-Based Apprenticeship Learning","created":"2021-07-20","cited_by_count":17,"area":"offlinerl"},{"id":"2207.00244","title":"Discriminator-Guided Model-Based Offline Imitation Learning","created":"2022-07-01","cited_by_count":17,"area":"offlinerl"},{"id":"2210.06479","title":"Real World Offline Reinforcement Learning with Realistic Data Source","created":"2022-10-12","cited_by_count":17,"area":"offlinerl"},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15,"area":"offlinerl"},{"id":"2309.03322","title":"REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation","created":"2023-09-06","cited_by_count":15,"area":"offlinerl"},{"id":"2106.05068","title":"Offline Inverse Reinforcement Learning","created":"2021-06-09","cited_by_count":14,"area":"offlinerl"},{"id":"2401.08957","title":"Learning from Imperfect Demonstrations with Self-Supervision for Robotic Manipulation","created":"2024-01-17","cited_by_count":14,"area":null},{"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":"2306.14534","title":"CEIL: Generalized Contextual Imitation Learning","created":"2023-06-26","cited_by_count":13,"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":"2108.08765","title":"Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation","created":"2021-08-19","cited_by_count":11,"area":"offlinerl"},{"id":"2306.13412","title":"CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning","created":"2023-06-23","cited_by_count":11,"area":"offlinerl"},{"id":"2503.01837","title":"Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning","created":"2025-03-03","cited_by_count":11,"area":"wm"},{"id":"2404.16779","title":"DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2406.08805","title":"A Dual Approach to Imitation Learning from Observations with Offline Datasets","created":"2024-06-13","cited_by_count":10,"area":"offlinerl"},{"id":"2502.20630","title":"Subtask-Aware Visual Reward Learning from Segmented Demonstrations","created":"2025-02-28","cited_by_count":10,"area":"deeprl"},{"id":"2402.13037","title":"Align Your Intents: Offline Imitation Learning via Optimal Transport","created":"2024-02-20","cited_by_count":8,"area":"offlinerl"},{"id":"2310.04706","title":"Offline Imitation Learning with Variational Counterfactual Reasoning","created":"2023-10-07","cited_by_count":7,"area":"offlinerl"},{"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":"2110.04698","title":"A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasets","created":"2021-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2201.08102","title":"Safe Deep RL in 3D Environments using Human Feedback","created":"2022-01-20","cited_by_count":5,"area":"alignment"},{"id":"2211.13337","title":"Multi-Environment Pretraining Enables Transfer to Action Limited Datasets","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2302.02788","title":"A Strong Baseline for Batch Imitation Learning","created":"2023-02-06","cited_by_count":5,"area":"offlinerl"},{"id":"2311.01331","title":"Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2410.03626","title":"Robust Offline Imitation Learning from Diverse Auxiliary Data","created":"2024-10-04","cited_by_count":5,"area":"offlinerl"},{"id":"2405.14790","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2303.01440","title":"Programmatic Imitation Learning from Unlabeled and Noisy Demonstrations","created":"2023-03-02","cited_by_count":3,"area":"offlinerl"},{"id":"2307.13101","title":"Contrastive Example-Based Control","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2311.01329","title":"A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2401.16452","title":"Context-Former: Stitching via Latent Conditioned Sequence Modeling","created":"2024-01-29","cited_by_count":3,"area":"offlinerl"},{"id":"2410.08751","title":"Zero-Shot Offline Imitation Learning via Optimal Transport","created":"2024-10-11","cited_by_count":3,"area":"offlinerl"},{"id":"2505.10760","title":"Counterfactual Behavior Cloning: Offline Imitation Learning from Imperfect Human Demonstrations","created":"2025-05-16","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":"2407.10839","title":"Offline Reinforcement Learning with Imputed Rewards","created":"2024-07-15","cited_by_count":2,"area":"alignment"},{"id":"2511.22555","title":"Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time Intervention","created":"2025-11-27","cited_by_count":2,"area":"vla"},{"id":"2212.08961","title":"Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2406.01065","title":"Causal prompting model-based offline reinforcement learning","created":"2024-06-03","cited_by_count":1,"area":"offlinerl"},{"id":"2307.12968","title":"A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning","created":"2023-07-24","cited_by_count":0,"area":"offlinerl"},{"id":"2402.03661","title":"Transductive Reward Inference on Graph","created":"2024-02-06","cited_by_count":0,"area":"offlinerl"},{"id":"2405.20351","title":"Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression","created":"2024-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2406.07117","title":"Augmenting Offline RL with Unlabeled Data","created":"2024-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2506.06793","title":"Minimal Ingredients for Reward Assignment from Expert Demonstrations","created":"2025-06-07","cited_by_count":0,"area":"offlinerl"},{"id":"2506.22008","title":"TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning","created":"2025-06-27","cited_by_count":0,"area":"offlinerl"},{"id":"2507.06701","title":"Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement","created":"2025-07-09","cited_by_count":0,"area":"offlinerl"},{"id":"2511.03616","title":"Going Beyond Expert Performance via Deep Implicit Imitation Reinforcement Learning","created":"2025-11-05","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":"2603.05440","title":"Latent Wasserstein Adversarial Imitation Learning","created":"2026-03-05","cited_by_count":0,"area":"offlinerl"},{"id":"2604.00258","title":"Hierarchical Apprenticeship Learning from Imperfect Demonstrations with Evolving Rewards","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.30843","title":"A Lecture Note on Offline RL and IRL, Part II: Foundations of Inverse Reinforcement Learning and Dynamic Discrete Choice Models","created":"2026-05-29","cited_by_count":0,"area":"offlinerl"},{"id":"2607.14180","title":"RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences","created":"2026-07-15","cited_by_count":0,"area":"wm"},{"id":"2609.38225","title":"SynIL: Leveraging Synergy for Offline Imitation Learning from Imperfect Demonstration Datasets","created":"2026-09-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}