{"total":15,"rows":[{"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":"2505.17389","title":"Bootstrapping Imitation Learning for Long-horizon Manipulation via Hierarchical Data Collection Space","created":"2025-05-23","cited_by_count":3,"area":"offlinerl"},{"id":"2605.05172","title":"When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning","created":"2026-05-06","cited_by_count":3,"area":"offlinerl"},{"id":"2605.12236","title":"TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning","created":"2026-05-12","cited_by_count":3,"area":"offlinerl"},{"id":"2604.03613","title":"Human-Robot Copilot for Data-Efficient Imitation Learning","created":"2026-04-04","cited_by_count":1,"area":"offlinerl"},{"id":"2604.10165","title":"MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks","created":"2026-04-11","cited_by_count":1,"area":"offlinerl"},{"id":"2606.09381","title":"ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration","created":"2026-06-08","cited_by_count":1,"area":"offlinerl"},{"id":"2601.15761","title":"Off-Policy Actor-Critic with Sigmoid-Bounded Entropy for Real-World Robot Learning","created":"2026-01-22","cited_by_count":0,"area":"offlinerl"},{"id":"2603.03960","title":"Structural Action Transformer for 3D Dexterous Manipulation","created":"2026-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2606.09615","title":"DexPIE: Stable Dexterous Policy Improvement from Real-World Experience","created":"2026-06-08","cited_by_count":0,"area":"offlinerl"},{"id":"2607.09866","title":"Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning","created":"2026-07-10","cited_by_count":0,"area":"offlinerl"},{"id":"2609.12749","title":"SCQ: Stabilizing Conservative Q-Learning with Sigmoid-Bounded Entropy","created":"2026-09-11","cited_by_count":0,"area":"offlinerl"},{"id":"2609.30023","title":"Res-HIL: Human-Guided Residual Reinforcement Learning for Sample-Efficient Dexterous Manipulation","created":"2026-09-24","cited_by_count":0,"area":"offlinerl"},{"id":"2610.05882","title":"Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning","created":"2026-10-05","cited_by_count":0,"area":"offlinerl"},{"id":"2610.17748","title":"I3L: Iterative Interactive Imitation Learning for Whole-Body Mobile Manipulation","created":"2026-10-13","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}