{"total":64,"rows":[{"id":"2112.03227","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","created":"2021-12-06","cited_by_count":584,"area":null},{"id":"2305.18459","title":"Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning","created":"2023-05-29","cited_by_count":115,"area":"diffusion"},{"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":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85,"area":"offlinerl"},{"id":"2210.05178","title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","created":"2022-10-11","cited_by_count":78,"area":"offlinerl"},{"id":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62,"area":"offlinerl"},{"id":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"id":"2205.08129","title":"Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space","created":"2022-05-17","cited_by_count":31,"area":null},{"id":"2305.17625","title":"Cross-Domain Policy Adaptation via Value-Guided Data Filtering","created":"2023-05-28","cited_by_count":31,"area":null},{"id":"2207.04703","title":"Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"2305.16683","title":"Future-conditioned Unsupervised Pretraining for Decision Transformer","created":"2023-05-26","cited_by_count":26,"area":"offlinerl"},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24,"area":"offlinerl"},{"id":"2212.00186","title":"Multi-Task Imitation Learning for Linear Dynamical Systems","created":"2022-12-01","cited_by_count":23,"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":"2210.04476","title":"Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks","created":"2022-10-10","cited_by_count":17,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2209.10447","title":"Hierarchical Decision Transformer","created":"2022-09-21","cited_by_count":16,"area":"offlinerl"},{"id":"2202.02929","title":"Model-Based Offline Meta-Reinforcement Learning with Regularization","created":"2022-02-07","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":"2407.17466","title":"Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning","created":"2024-07-24","cited_by_count":15,"area":"deeprl"},{"id":"2401.03306","title":"MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning","created":"2024-01-06","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":"2408.04190","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","created":"2024-08-08","cited_by_count":14,"area":"alignment"},{"id":"2310.18687","title":"Unsupervised Behavior Extraction via Random Intent Priors","created":"2023-10-28","cited_by_count":13,"area":"offlinerl"},{"id":"2203.08949","title":"Latent-Variable Advantage-Weighted Policy Optimization for Offline RL","created":"2022-03-16","cited_by_count":12,"area":"offlinerl"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2203.07413","title":"Switch Trajectory Transformer with Distributional Value Approximation for Multi-Task Reinforcement Learning","created":"2022-03-14","cited_by_count":11,"area":null},{"id":"2408.10556","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","created":"2024-08-20","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":"2410.05026","title":"Active Fine-Tuning of Multi-Task Policies","created":"2024-10-07","cited_by_count":9,"area":"offlinerl"},{"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":"2305.03097","title":"Federated Ensemble-Directed Offline Reinforcement Learning","created":"2023-05-04","cited_by_count":6,"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":"2311.08290","title":"On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2402.04933","title":"Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits","created":"2024-02-07","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":"2204.05893","title":"Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Data","created":"2022-04-12","cited_by_count":5,"area":null},{"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":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2305.13804","title":"OER: Offline Experience Replay for Continual Offline Reinforcement Learning","created":"2023-05-23","cited_by_count":4,"area":"offlinerl"},{"id":"2310.09924","title":"Deep Reinforcement Learning with Explicit Context Representation","created":"2023-10-15","cited_by_count":3,"area":null},{"id":"2408.15593","title":"Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning","created":"2024-08-28","cited_by_count":3,"area":"offlinerl"},{"id":"2507.06615","title":"Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance","created":"2025-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2403.07261","title":"Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation","created":"2024-03-12","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":"2406.14054","title":"Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing","created":"2024-06-20","cited_by_count":2,"area":"offlinerl"},{"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":"2410.22728","title":"Offline Behavior Distillation","created":"2024-10-30","cited_by_count":2,"area":"deeprl"},{"id":"2204.11596","title":"A Simple Structure For Building A Robust Model","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2402.11367","title":"Multi Task Inverse Reinforcement Learning for Common Sense Reward","created":"2024-02-17","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":"2510.19562","title":"DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2512.06692","title":"State Diversity Matters in Offline Behavior Distillation","created":"2025-12-07","cited_by_count":1,"area":"offlinerl"},{"id":"2309.15603","title":"Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularization","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2310.01827","title":"Learning and reusing primitive behaviours to improve Hindsight Experience Replay sample efficiency","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2405.07943","title":"Decision Mamba Architectures","created":"2024-05-13","cited_by_count":0,"area":"ssm"},{"id":"2506.06793","title":"Minimal Ingredients for Reward Assignment from Expert Demonstrations","created":"2025-06-07","cited_by_count":0,"area":"offlinerl"},{"id":"2509.20766","title":"Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning","created":"2025-09-25","cited_by_count":0,"area":"deeprl"},{"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":"2512.20220","title":"Generalisation in Multitask Fitted Q-Iteration and Offline Q-learning","created":"2025-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2607.03903","title":"CDCP: Conditional Diffusion Model with Contextual Prompts for Multi-task Offline Safe Reinforcement Learning","created":"2026-07-04","cited_by_count":0,"area":"diffusion"},{"id":"2609.03667","title":"Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning","created":"2026-09-03","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}