ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning

arXiv:2609.37131 · cs.RO · Submitted 2026-09-29 · Read on arXiv

cs.RO

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: 8 pages, 7 figures. Shaoyin Luo and Song Wang contributed equally to this work

Project page: https://anonymous.4open.science/w/ReF-HIL-7762

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 30× in this paper · explained in 4 episodes
• Human-in-the-Loop — 10× in this paper · explained in 3 episodes
• Actor — 8× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Q-learning — 3× in this paper · explained in 3 episodes
• Action Space — 2× in this paper · explained in 1 episode
• Deep Reinforcement Learning — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Credit assignment — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Sim-to-Real Transfer — 1× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

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
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies