{"total":50,"rows":[{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2310.15145","title":"Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning","created":"2023-10-23","cited_by_count":54,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2301.09816","title":"SMART: Self-supervised Multi-task pretrAining with contRol Transformers","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2208.09052","title":"A Review of Uncertainty for Deep Reinforcement Learning","created":"2022-08-18","cited_by_count":40,"area":null},{"id":"2507.07986","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","created":"2025-07-10","cited_by_count":34,"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":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2210.04561","title":"A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning","created":"2022-10-10","cited_by_count":25,"area":null},{"id":"2210.06601","title":"Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks","created":"2022-10-12","cited_by_count":25,"area":null},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2211.15457","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":19,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2303.02618","title":"Ensemble Reinforcement Learning: A Survey","created":"2023-03-05","cited_by_count":16,"area":null},{"id":"2502.05932","title":"Skill Expansion and Composition in Parameter Space","created":"2025-02-09","cited_by_count":14,"area":null},{"id":"2410.18076","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","created":"2024-10-23","cited_by_count":13,"area":null},{"id":"2311.15951","title":"Replay across Experiments: A Natural Extension of Off-Policy RL","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2402.06187","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2205.08716","title":"No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2309.12038","title":"Uncertainty-driven Exploration Strategies for Online Grasp Learning","created":"2023-09-21","cited_by_count":6,"area":null},{"id":"2412.13492","title":"Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2607.01111","title":"FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement","created":"2026-07-01","cited_by_count":5,"area":null},{"id":"2211.15930","title":"Offline Supervised Learning V.S. Online Direct Policy Optimization: A Comparative Study and A Unified Training Paradigm for Neural Network-Based Optimal Feedback Control","created":"2022-11-29","cited_by_count":3,"area":null},{"id":"2310.11531","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2312.04386","title":"Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2408.13567","title":"Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning","created":"2024-08-24","cited_by_count":3,"area":null},{"id":"2412.04426","title":"Towards Fast Safe Online Reinforcement Learning via Policy Finetuning","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2302.01399","title":"Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning","created":"2023-02-02","cited_by_count":2,"area":null},{"id":"2306.11271","title":"Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2409.03996","title":"Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance","created":"2024-09-06","cited_by_count":2,"area":null},{"id":"2503.06145","title":"Adaptive UAV-Assisted Hierarchical Federated Learning: Optimizing Energy, Latency, and Resilience for Dynamic Smart IoT","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2512.21925","title":"Hybrid Combinatorial Multi-armed Bandits with Probabilistically Triggered Arms","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2310.15059","title":"Robot Skill Generalization via Keypoint Integrated Soft Actor-Critic Gaussian Mixture Models","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.15669","title":"Exploiting Policy Idling for Dexterous Manipulation","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2312.02665","title":"Lights out: training RL agents robust to temporary blindness","created":"2023-12-05","cited_by_count":0,"area":null},{"id":"2502.00288","title":"Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2505.00913","title":"Fine-Tuning without Performance Degradation","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2505.12759","title":"Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2605.10289","title":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2608.19684","title":"Learning Hierarchical Skill Policies with Offline Quality-Diversity Reinforcement Learning","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.30512","title":"Trajectory-Initialized Neural Double Q-Routing for Large-Scale Overhead Hoist Transport Systems","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}