RESEARCH PAPERYear 2025

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning

Jianlan Luo; Charles Xu; Jeffrey Wu; Sergey Levine

Classification

View four quadrants
Major category
Foundational work
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. HIL-SERL is a pre-2026 model-free robotic RL foundation for policy post-training with demonstrations and human corrections. Its actor-critic and physical feedback do not constitute a future-world predictor or reusable WAM encoder/backbone. The manuscript cites it as RL training background. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX