# FERRET: Using Environment Edits as a Corrective Signal for Reward Learning

- Source: arXiv cs.RO
- Published: 2026-10-27T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/f34cav3u1hi0zntos1171v928
- Original: https://arxiv.org/abs/2610.35659

## Summary

The authors propose environment edits as a complementary form of feedback for robot corrections: with the robot's motion held constant, a human edits the scene so that the only explanation for the edit is the moved object. They introduce FERRET (Feature Learning from Environmental and Robot-Relational Edit Traces), which learns preferences from both robot corrections and environment corrections, and they show that environment edits can disambiguate features and learn preferences that robot corrections alone cannot.