{"total":18,"rows":[{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2507.07986","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","created":"2025-07-10","cited_by_count":34,"area":null},{"id":"2310.01737","title":"Blending Imitation and Reinforcement Learning for Robust Policy Improvement","created":"2023-10-03","cited_by_count":17,"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":"2310.20287","title":"Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents","created":"2023-10-31","cited_by_count":12,"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":"2309.02671","title":"RLSynC: Offline-Online Reinforcement Learning for Synthon Completion","created":"2023-09-06","cited_by_count":4,"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":"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":"2305.17623","title":"On the Value of Myopic Behavior in Policy Reuse","created":"2023-05-28","cited_by_count":1,"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":"2506.01568","title":"Trajectory First: A Curriculum for Discovering Diverse Policies","created":"2025-06-02","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}