ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning
cs.RO
Submitted: 2026-09-29
Updated: 2026-09-29
Project page: https://anonymous.4open.science/w/ReF-HIL-7762
Terminology
Sources
- Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation
- OHP-RL: Online Human Preference as Guidance in Reinforcement Learning for Robot Manipulation
- AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
- Real-world Reinforcement Learning from Suboptimal Interventions
- From Action Labels to Sets: Rethinking Action Supervision for Imitation Learning from Corrective Feedback
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving