{"total":62,"rows":[{"id":"2210.00030","title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","created":"2022-09-30","cited_by_count":395,"area":"offlinerl"},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2502.14819","title":"Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models","created":"2025-02-20","cited_by_count":89,"area":null},{"id":"2210.11435","title":"Learning and Retrieval from Prior Data for Skill-based Imitation Learning","created":"2022-10-20","cited_by_count":77,"area":"offlinerl"},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2303.13971","title":"Optimal Transport for Offline Imitation Learning","created":"2023-03-24","cited_by_count":42,"area":"offlinerl"},{"id":"2210.06518","title":"Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories","created":"2022-10-12","cited_by_count":28,"area":"offlinerl"},{"id":"2504.16925","title":"Latent Diffusion Planning for Imitation Learning","created":"2025-04-23","cited_by_count":26,"area":"diffusion"},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2502.03369","title":"Learning from Active Human Involvement through Proxy Value Propagation","created":"2025-02-05","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":"2405.06192","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","created":"2024-05-10","cited_by_count":18,"area":"offlinerl"},{"id":"2211.02100","title":"Contrastive Value Learning: Implicit Models for Simple Offline RL","created":"2022-11-03","cited_by_count":15,"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":"2502.04327","title":"Value-Based Deep RL Scales Predictably","created":"2025-02-06","cited_by_count":15,"area":"deeprl"},{"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":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","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":"2405.17476","title":"How to Leverage Diverse Demonstrations in Offline Imitation Learning","created":"2024-05-24","cited_by_count":12,"area":"offlinerl"},{"id":"2302.13493","title":"The Provable Benefits of Unsupervised Data Sharing for Offline Reinforcement Learning","created":"2023-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2210.00498","title":"EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model","created":"2022-10-02","cited_by_count":8,"area":null},{"id":"2402.13037","title":"Align Your Intents: Offline Imitation Learning via Optimal Transport","created":"2024-02-20","cited_by_count":8,"area":"offlinerl"},{"id":"2403.00929","title":"PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learning","created":"2024-03-01","cited_by_count":8,"area":"offlinerl"},{"id":"2411.03169","title":"Pre-trained Visual Dynamics Representations for Efficient Policy Learning","created":"2024-11-05","cited_by_count":8,"area":"deeprl"},{"id":"2412.18256","title":"Robust Semi-Supervised Learning in Open Environments","created":"2024-12-24","cited_by_count":8,"area":null},{"id":"2305.15260","title":"Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning","created":"2023-05-24","cited_by_count":7,"area":"wm"},{"id":"2404.19346","title":"Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning","created":"2024-04-30","cited_by_count":7,"area":"offlinerl"},{"id":"2302.00671","title":"QMP: Q-switch Mixture of Policies for Multi-Task Behavior Sharing","created":"2023-02-01","cited_by_count":6,"area":null},{"id":"2405.00746","title":"Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning","created":"2024-04-30","cited_by_count":6,"area":"deeprl"},{"id":"2405.17477","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","created":"2024-05-24","cited_by_count":6,"area":"offlinerl"},{"id":"2405.14214","title":"A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points","created":"2024-05-23","cited_by_count":5,"area":"deeprl"},{"id":"2410.03626","title":"Robust Offline Imitation Learning from Diverse Auxiliary Data","created":"2024-10-04","cited_by_count":5,"area":"offlinerl"},{"id":"2307.03973","title":"Autonomy 2.0: The Quest for Economies of Scale","created":"2023-07-08","cited_by_count":4,"area":null},{"id":"2310.08841","title":"Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environments","created":"2023-10-13","cited_by_count":4,"area":"offlinerl"},{"id":"2503.04969","title":"Data-Efficient Learning from Human Interventions for Mobile Robots","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2307.13101","title":"Contrastive Example-Based Control","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2404.07465","title":"Offline Reinforcement Learning with Domain-Unlabeled Data","created":"2024-04-11","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":"2303.02265","title":"Learning to Influence Human Behavior with Offline Reinforcement Learning","created":"2023-03-03","cited_by_count":2,"area":"offlinerl"},{"id":"2308.03882","title":"Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations","created":"2023-08-07","cited_by_count":2,"area":"offlinerl"},{"id":"2404.05950","title":"Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction","created":"2024-04-09","cited_by_count":2,"area":"deeprl"},{"id":"2408.12307","title":"Leveraging Unlabeled Data Sharing through Kernel Function Approximation in Offline Reinforcement Learning","created":"2024-08-22","cited_by_count":2,"area":"offlinerl"},{"id":"2402.18617","title":"ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games","created":"2024-02-28","cited_by_count":1,"area":"offlinerl"},{"id":"2408.07753","title":"How to Solve Contextual Goal-Oriented Problems with Offline Datasets?","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2502.19544","title":"Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data","created":"2025-02-26","cited_by_count":1,"area":"wm"},{"id":"2503.22524","title":"Robust Offline Imitation Learning Through State-level Trajectory Stitching","created":"2025-03-28","cited_by_count":1,"area":"offlinerl"},{"id":"2504.08704","title":"Offline Reinforcement Learning using Human-Aligned Reward Labeling for Autonomous Emergency Braking in Occluded Pedestrian Crossing","created":"2025-04-11","cited_by_count":1,"area":"offlinerl"},{"id":"2505.05701","title":"Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning","created":"2025-05-09","cited_by_count":1,"area":"offlinerl"},{"id":"2505.06482","title":"Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach","created":"2025-05-10","cited_by_count":1,"area":"offlinerl"},{"id":"2402.03661","title":"Transductive Reward Inference on Graph","created":"2024-02-06","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":"2408.05285","title":"Semi-Supervised One-Shot Imitation Learning","created":"2024-08-09","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":"2510.00144","title":"Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited Feedback","created":"2025-09-30","cited_by_count":0,"area":"alignment"},{"id":"2510.07760","title":"VAO: Validation-Aligned Optimization for Cross-Task Generative Auto-Bidding","created":"2025-10-09","cited_by_count":0,"area":null},{"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":"2610.12140","title":"Leveraging Human-In-The-Loop Demonstrations in Reinforcement Learning for Digital Twin-Driven Robot Flexibility","created":"2026-10-08","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}