# Physical Intelligence proposes RLT: efficient online reinforcement learning for fine manipulation

- Source: Physical Intelligence
- Published: 2026-03-18T16:00:00.000Z
- RoboHot: https://robohot.news/en/items/ifwrnjxdzo9sfzd4ja7ikf72i
- Original: https://www.pi.website/research/rlt

## Summary

Physical Intelligence proposes a new method called RL tokens (RLT), in which a vision-language-action model (VLA) outputs a special token to interface with a lightweight online reinforcement learning policy, improving the speed and success rate of fine manipulation phases with only a small amount of real data.

## Why it matters

The original clearly explains the interface design between the VLA and lightweight online reinforcement learning and provides speedup data on four tasks, so readers can assess whether this type of method applies to their own fine manipulation tasks.