{"total":113,"rows":[{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568,"area":"offlinerl"},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725,"area":"offlinerl"},{"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":"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":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304,"area":"offlinerl"},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"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":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215,"area":"offlinerl"},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2204.06252","title":"What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data","created":"2022-04-13","cited_by_count":138,"area":"offlinerl"},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138,"area":"offlinerl"},{"id":"2010.12083","title":"Language-Conditioned Imitation Learning for Robot Manipulation Tasks","created":"2020-10-22","cited_by_count":136,"area":"offlinerl"},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136,"area":"offlinerl"},{"id":"2102.06203","title":"Proof Artifact Co-training for Theorem Proving with Language Models","created":"2021-02-11","cited_by_count":132,"area":"offlinerl"},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125,"area":"offlinerl"},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121,"area":"offlinerl"},{"id":"2110.07342","title":"FILM: Following Instructions in Language with Modular Methods","created":"2021-10-12","cited_by_count":121,"area":"offlinerl"},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2302.00935","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","created":"2023-02-02","cited_by_count":104,"area":"offlinerl"},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103,"area":"offlinerl"},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91,"area":"offlinerl"},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75,"area":"offlinerl"},{"id":"2009.07253","title":"Autoregressive Knowledge Distillation through Imitation Learning","created":"2020-09-15","cited_by_count":74,"area":"offlinerl"},{"id":"2311.02058","title":"LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery","created":"2023-11-03","cited_by_count":67,"area":"offlinerl"},{"id":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63,"area":"offlinerl"},{"id":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63,"area":"offlinerl"},{"id":"2210.03112","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","created":"2022-10-06","cited_by_count":60,"area":"offlinerl"},{"id":"2310.17086","title":"Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression","created":"2023-10-26","cited_by_count":49,"area":"offlinerl"},{"id":"2211.12740","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","created":"2022-11-23","cited_by_count":45,"area":"offlinerl"},{"id":"2409.12192","title":"DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control","created":"2024-09-18","cited_by_count":44,"area":"offlinerl"},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38,"area":"offlinerl"},{"id":"2206.08569","title":"Bootstrapped Transformer for Offline Reinforcement Learning","created":"2022-06-17","cited_by_count":37,"area":"offlinerl"},{"id":"2408.04380","title":"Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations","created":"2024-08-08","cited_by_count":35,"area":"offlinerl"},{"id":"2210.13846","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","created":"2022-10-25","cited_by_count":34,"area":"offlinerl"},{"id":"2108.00385","title":"Transformer-based deep imitation learning for dual-arm robot manipulation","created":"2021-08-01","cited_by_count":32,"area":"offlinerl"},{"id":"2405.17098","title":"Q-value Regularized Transformer for Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":29,"area":"offlinerl"},{"id":"2305.16683","title":"Future-conditioned Unsupervised Pretraining for Decision Transformer","created":"2023-05-26","cited_by_count":26,"area":"offlinerl"},{"id":"2310.03022","title":"Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making","created":"2023-10-04","cited_by_count":26,"area":"offlinerl"},{"id":"2311.03351","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","created":"2023-11-06","cited_by_count":26,"area":"offlinerl"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2505.10251","title":"SRT-H: A Hierarchical Framework for Autonomous Surgery via Language Conditioned Imitation Learning","created":"2025-05-15","cited_by_count":26,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2307.15690","title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","created":"2023-07-28","cited_by_count":23,"area":"offlinerl"},{"id":"2304.04591","title":"For Pre-Trained Vision Models in Motor Control, Not All Policy Learning Methods are Created Equal","created":"2023-04-10","cited_by_count":22,"area":"offlinerl"},{"id":"2306.14069","title":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","created":"2023-06-24","cited_by_count":22,"area":"offlinerl"},{"id":"1909.12200","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","created":"2019-09-26","cited_by_count":18,"area":"offlinerl"},{"id":"2402.07876","title":"Policy Improvement using Language Feedback Models","created":"2024-02-12","cited_by_count":16,"area":"offlinerl"},{"id":"2005.12801","title":"Active Imitation Learning with Noisy Guidance","created":"2020-05-26","cited_by_count":15,"area":"offlinerl"},{"id":"2406.09738","title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","created":"2024-06-14","cited_by_count":15,"area":"offlinerl"},{"id":"2211.14655","title":"How Crucial is Transformer in Decision Transformer?","created":"2022-11-26","cited_by_count":14,"area":"offlinerl"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2410.00064","title":"M2Distill: Multi-Modal Distillation for Lifelong Imitation Learning","created":"2024-09-30","cited_by_count":11,"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":"2307.03406","title":"Goal-Conditioned Predictive Coding for Offline Reinforcement Learning","created":"2023-07-07","cited_by_count":10,"area":"offlinerl"},{"id":"2310.00771","title":"Pre-training with Synthetic Data Helps Offline Reinforcement Learning","created":"2023-10-01","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":"2211.08016","title":"Contextual Transformer for Offline Meta Reinforcement Learning","created":"2022-11-15","cited_by_count":7,"area":"offlinerl"},{"id":"2211.09817","title":"On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning","created":"2022-11-17","cited_by_count":7,"area":"offlinerl"},{"id":"2405.11206","title":"Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses","created":"2024-05-18","cited_by_count":7,"area":"offlinerl"},{"id":"2502.15679","title":"BOSS: Benchmark for Observation Space Shift in Long-Horizon Task","created":"2025-02-21","cited_by_count":7,"area":"offlinerl"},{"id":"2307.07091","title":"Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning","created":"2023-07-13","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":"2410.03408","title":"Predictive Coding for Decision Transformer","created":"2024-10-04","cited_by_count":6,"area":"offlinerl"},{"id":"2312.05925","title":"Language-Conditioned Semantic Search-Based Policy for Robotic Manipulation Tasks","created":"2023-12-10","cited_by_count":5,"area":"offlinerl"},{"id":"2407.20299","title":"Dataset Distillation for Offline Reinforcement Learning","created":"2024-07-29","cited_by_count":5,"area":"offlinerl"},{"id":"2504.01301","title":"Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers","created":"2025-04-02","cited_by_count":5,"area":"offlinerl"},{"id":"2504.15046","title":"Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision","created":"2025-04-21","cited_by_count":5,"area":"offlinerl"},{"id":"2207.13082","title":"Offline Reinforcement Learning at Multiple Frequencies","created":"2022-07-26","cited_by_count":4,"area":"offlinerl"},{"id":"2405.18757","title":"Multi-objective Cross-task Learning via Goal-conditioned GPT-based Decision Transformers for Surgical Robot Task Automation","created":"2024-05-29","cited_by_count":4,"area":"offlinerl"},{"id":"2504.04395","title":"Human-Level Competitive Pok\\'emon via Scalable Offline Reinforcement Learning with Transformers","created":"2025-04-06","cited_by_count":4,"area":"offlinerl"},{"id":"2511.04812","title":"Multimodal Diffusion Forcing for Forceful Manipulation","created":"2025-11-06","cited_by_count":4,"area":"offlinerl"},{"id":"2311.09350","title":"Generalizable Imitation Learning Through Pre-Trained Representations","created":"2023-11-15","cited_by_count":3,"area":"offlinerl"},{"id":"2401.16452","title":"Context-Former: Stitching via Latent Conditioned Sequence Modeling","created":"2024-01-29","cited_by_count":3,"area":"offlinerl"},{"id":"2402.17511","title":"Rethinking Mutual Information for Language Conditioned Skill Discovery on Imitation Learning","created":"2024-02-27","cited_by_count":3,"area":"offlinerl"},{"id":"2410.17744","title":"Learning Versatile Skills with Curriculum Masking","created":"2024-10-23","cited_by_count":3,"area":"offlinerl"},{"id":"2102.10774","title":"Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning","created":"2021-02-22","cited_by_count":2,"area":"offlinerl"},{"id":"2301.09770","title":"Language-guided Task Adaptation for Imitation Learning","created":"2023-01-24","cited_by_count":2,"area":"offlinerl"},{"id":"2311.00094","title":"A Tractable Inference Perspective of Offline RL","created":"2023-10-31","cited_by_count":2,"area":"offlinerl"},{"id":"2406.08238","title":"Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning","created":"2024-06-12","cited_by_count":2,"area":"offlinerl"},{"id":"2505.10010","title":"ImagineBench: Evaluating Reinforcement Learning with Large Language Model Rollouts","created":"2025-05-15","cited_by_count":2,"area":"offlinerl"},{"id":"2508.01167","title":"T2S: Tokenized Skill Scaling for Lifelong Imitation Learning","created":"2025-08-02","cited_by_count":2,"area":"offlinerl"},{"id":"2509.04628","title":"Action Chunking with Transformers for Image-Based Spacecraft Guidance and Control","created":"2025-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"2602.07496","title":"CoMI-IRL: Contrastive Multi-Intention Inverse Reinforcement Learning","created":"2026-02-07","cited_by_count":2,"area":"offlinerl"},{"id":"1909.11373","title":"Multi-task Batch Reinforcement Learning with Metric Learning","created":"2019-09-25","cited_by_count":1,"area":"offlinerl"},{"id":"2305.07856","title":"Stackelberg Decision Transformer for Asynchronous Action Coordination in Multi-Agent Systems","created":"2023-05-13","cited_by_count":1,"area":"offlinerl"},{"id":"2310.02405","title":"PCGPT: Procedural Content Generation via Transformers","created":"2023-10-03","cited_by_count":1,"area":"offlinerl"},{"id":"2310.16566","title":"Model-enhanced Contrastive Reinforcement Learning for Sequential Recommendation","created":"2023-10-25","cited_by_count":1,"area":"offlinerl"},{"id":"2402.05306","title":"Interactive Symbolic Regression through Offline Reinforcement Learning: A Co-Design Framework","created":"2024-02-07","cited_by_count":1,"area":"offlinerl"},{"id":"2406.01065","title":"Causal prompting model-based offline reinforcement learning","created":"2024-06-03","cited_by_count":1,"area":"offlinerl"},{"id":"2411.11406","title":"Bridging the Resource Gap: Deploying Advanced Imitation Learning Models onto Affordable Embedded Platforms","created":"2024-11-18","cited_by_count":1,"area":"offlinerl"},{"id":"2510.09497","title":"Toward Autonomous Soft Robotic Endovascular Navigation via Imitation Learning","created":"2025-10-10","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":"2608.17323","title":"ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback","created":"2026-08-18","cited_by_count":1,"area":"offlinerl"},{"id":"2004.06229","title":"Imitation Learning for Fashion Style Based on Hierarchical Multimodal Representation","created":"2020-04-13","cited_by_count":0,"area":"offlinerl"},{"id":"2211.04583","title":"Wall Street Tree Search: Risk-Aware Planning for Offline Reinforcement Learning","created":"2022-11-06","cited_by_count":0,"area":"offlinerl"},{"id":"2303.07846","title":"Sample-efficient Adversarial Imitation Learning","created":"2023-03-14","cited_by_count":0,"area":"offlinerl"},{"id":"2310.08823","title":"Distance-rank Aware Sequential Reward Learning for Inverse Reinforcement Learning with Sub-optimal Demonstrations","created":"2023-10-13","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"}],"next_cursor":"100"}