{"total":71,"rows":[{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111,"area":"offlinerl"},{"id":"2201.13425","title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","created":"2022-01-31","cited_by_count":96,"area":"offlinerl"},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"id":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50,"area":"offlinerl"},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"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":"2305.02968","title":"Masked Trajectory Models for Prediction, Representation, and Control","created":"2023-05-04","cited_by_count":42,"area":"offlinerl"},{"id":"2004.09395","title":"Energy-Based Imitation Learning","created":"2020-04-20","cited_by_count":40,"area":"offlinerl"},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40,"area":"offlinerl"},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36,"area":"offlinerl"},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2201.11861","title":"The Challenges of Exploration for Offline Reinforcement Learning","created":"2022-01-27","cited_by_count":26,"area":"offlinerl"},{"id":"2305.16683","title":"Future-conditioned Unsupervised Pretraining for Decision Transformer","created":"2023-05-26","cited_by_count":26,"area":"offlinerl"},{"id":"2205.15397","title":"Minimax Optimal Online Imitation Learning via Replay Estimation","created":"2022-05-30","cited_by_count":25,"area":"offlinerl"},{"id":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"id":"2105.12034","title":"Hyperparameter Selection for Imitation Learning","created":"2021-05-25","cited_by_count":17,"area":"offlinerl"},{"id":"2108.04763","title":"Imitation Learning by Reinforcement Learning","created":"2021-08-10","cited_by_count":17,"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":"2208.07811","title":"Towards Informed Design and Validation Assistance in Computer Games Using Imitation Learning","created":"2022-08-15","cited_by_count":13,"area":"offlinerl"},{"id":"2412.04368","title":"Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weighting","created":"2024-12-05","cited_by_count":12,"area":"offlinerl"},{"id":"2506.07505","title":"Reinforcement Learning via Implicit Imitation Guidance","created":"2025-06-09","cited_by_count":12,"area":"offlinerl"},{"id":"2204.11446","title":"Imitation Learning from Observations under Transition Model Disparity","created":"2022-04-25","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":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2108.01867","title":"A Pragmatic Look at Deep Imitation Learning","created":"2021-08-04","cited_by_count":9,"area":"offlinerl"},{"id":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2310.08558","title":"Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias","created":"2023-10-12","cited_by_count":7,"area":"offlinerl"},{"id":"2411.01894","title":"Efficient Active Imitation Learning with Random Network Distillation","created":"2024-11-04","cited_by_count":7,"area":"offlinerl"},{"id":"2012.01365","title":"DERAIL: Diagnostic Environments for Reward And Imitation Learning","created":"2020-12-02","cited_by_count":6,"area":"offlinerl"},{"id":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6,"area":"offlinerl"},{"id":"2312.03446","title":"Visual Hindsight Self-Imitation Learning for Interactive Navigation","created":"2023-12-05","cited_by_count":6,"area":"offlinerl"},{"id":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","cited_by_count":6,"area":"offlinerl"},{"id":"1910.12154","title":"ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations","created":"2019-10-26","cited_by_count":5,"area":"offlinerl"},{"id":"2011.09586","title":"SAFARI: Safe and Active Robot Imitation Learning with Imagination","created":"2020-11-18","cited_by_count":5,"area":"offlinerl"},{"id":"2010.06962","title":"Self-Imitation Learning for Robot Tasks with Sparse and Delayed Rewards","created":"2020-10-14","cited_by_count":4,"area":"offlinerl"},{"id":"2206.01085","title":"Incorporating Explicit Uncertainty Estimates into Deep Offline Reinforcement Learning","created":"2022-06-02","cited_by_count":4,"area":"offlinerl"},{"id":"2310.05723","title":"Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning","created":"2023-10-09","cited_by_count":4,"area":"offlinerl"},{"id":"2403.13097","title":"Simple Ingredients for Offline Reinforcement Learning","created":"2024-03-19","cited_by_count":4,"area":"offlinerl"},{"id":"2002.08803","title":"Support-weighted Adversarial Imitation Learning","created":"2020-02-20","cited_by_count":3,"area":"offlinerl"},{"id":"2103.00098","title":"Reducing Conservativeness Oriented Offline Reinforcement Learning","created":"2021-02-27","cited_by_count":3,"area":"offlinerl"},{"id":"2211.16838","title":"Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation","created":"2022-11-30","cited_by_count":3,"area":"offlinerl"},{"id":"2503.11339","title":"Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model","created":"2025-03-14","cited_by_count":3,"area":"offlinerl"},{"id":"2204.07404","title":"Divide & Conquer Imitation Learning","created":"2022-04-15","cited_by_count":2,"area":"offlinerl"},{"id":"2210.10999","title":"Task Phasing: Automated Curriculum Learning from Demonstrations","created":"2022-10-20","cited_by_count":2,"area":"offlinerl"},{"id":"2402.01057","title":"Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning","created":"2024-02-01","cited_by_count":2,"area":"offlinerl"},{"id":"2509.03790","title":"What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?","created":"2025-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"2201.03834","title":"STIR$^2$: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks","created":"2022-01-11","cited_by_count":1,"area":"offlinerl"},{"id":"2502.04141","title":"Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning","created":"2025-02-06","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":"2505.21119","title":"Universal Value-Function Uncertainties","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"id":"2507.12815","title":"From Novelty to Imitation: Self-Distilled Rewards for Offline Reinforcement Learning","created":"2025-07-17","cited_by_count":1,"area":"offlinerl"},{"id":"2602.14844","title":"Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment","created":"2026-02-16","cited_by_count":1,"area":"offlinerl"},{"id":"2603.04845","title":"Task-Relevant and Irrelevant Region-Aware Augmentation for Generalizable Vision-Based Imitation Learning in Agricultural Manipulation","created":"2026-03-05","cited_by_count":1,"area":"offlinerl"},{"id":"2604.25496","title":"Improving Zero-Shot Offline RL via Behavioral Task Sampling","created":"2026-04-28","cited_by_count":1,"area":"offlinerl"},{"id":"2209.04100","title":"Task-Agnostic Learning to Accomplish New Tasks","created":"2022-09-09","cited_by_count":0,"area":"offlinerl"},{"id":"2211.08251","title":"Offline Reinforcement Learning with Adaptive Behavior Regularization","created":"2022-11-15","cited_by_count":0,"area":"offlinerl"},{"id":"2310.19805","title":"Improving Offline-to-Online Reinforcement Learning with Q Conditioned State Entropy Exploration","created":"2023-10-07","cited_by_count":0,"area":"offlinerl"},{"id":"2503.06893","title":"Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning","created":"2025-03-10","cited_by_count":0,"area":"offlinerl"},{"id":"2506.13958","title":"Toward Explainable Offline RL: Analyzing Representations in Intrinsically Motivated Decision Transformers","created":"2025-06-16","cited_by_count":0,"area":"offlinerl"},{"id":"2506.19643","title":"Unsupervised Data Generation for Offline Reinforcement Learning: A Perspective from Model","created":"2025-06-24","cited_by_count":0,"area":"offlinerl"},{"id":"2509.03206","title":"Autonomous Learning From Success and Failure: Goal-Conditioned Supervised Learning with Negative Feedback","created":"2025-09-03","cited_by_count":0,"area":"offlinerl"},{"id":"2509.26294","title":"Noise-Guided Transport for Imitation Learning","created":"2025-09-30","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":"2603.18326","title":"Escaping Offline Pessimism: Vector-Field Reward Shaping for Safe Frontier Exploration","created":"2026-03-18","cited_by_count":0,"area":"offlinerl"},{"id":"2605.17017","title":"When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited","created":"2026-05-16","cited_by_count":0,"area":"offlinerl"},{"id":"2608.22284","title":"Learning from the Test: Self-Referential Differential Testing for Deep RL Agents","created":"2026-08-23","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}