跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.10280 · v1

Who Taught the Robot That? Removing One User's Corrections from a Robot Policy That Learns Online

首次提交 2026-11-07 06:25
版本更新 2026-11-07 06:25
雷达观测 2026-11-10 10:11
arXiv ↗PDF ↗

摘要

A robot that keeps learning after deployment is corrected by several people in turn, and one of them may later ask to be removed. We show that whether the robot can forget that person depends on how people correct it. The goal of removal is the robot that would exist if the person had never been there, which we compute exactly in two simulated tasks with scripted users. When users correct the robot by taking over control, an ordered log of training updates is enough: retraining on the remaining sessions in their original order gives a robot as close to the goal as training noise allows. Deleting the person's data and retraining in one pass does not, even when the other users' corrections do not depend on the removed person, because it loses the order of training. When users only nudge the robot's action, the other users' corrections carry the removed person's influence, and no method we tested recovers the goal robot. Continuing to train without the person removes most of their habits, but not what their data in the training buffer keep alive. The log can identify one clearly harmful user, but not rank users by influence better than counting their corrections.

作者备注:Accepted at the HumanRLI Workshop at CoRL 2026

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-07 06:25 · 最新观测版本

Who Taught the Robot That? Removing One User's Corrections from a Robot Policy That Learns Online

A robot that keeps learning after deployment is corrected by several people in turn, and one of them may later ask to be removed. We show that whether the robot can forget that person depends on how people correct it. The goal of removal is the robot that would exist if the person had never been there, which we compute exactly in two simulated tasks with scripted users. When users correct the robot by taking over control, an ordered log of training updates is enough: retraining on the remaining sessions in their original order gives a robot as close to the goal as training noise allows. Deleting the person's data and retraining in one pass does not, even when the other users' corrections do not depend on the removed person, because it loses the order of training. When users only nudge the robot's action, the other users' corrections carry the removed person's influence, and no method we tested recovers the goal robot. Continuing to train without the person removes most of their habits, but not what their data in the training buffer keep alive. The log can identify one clearly harmful user, but not rank users by influence better than counting their corrections.

查看此版本解读 →查看此版本原文 ↗