跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2608.11229 · v2

ToM-2 Understanding Statements for Teacher-Guided Preference Learning

首次提交 2026-07-30 02:44
版本更新 2026-11-16 12:38
雷达观测 2026-11-17 17:12
arXiv ↗PDF ↗

摘要

Preference learning is a powerful tool for reward learning, but treats the teacher as a passive oracle that answers queries driven by the learner. This learner-guided query selection ignores the teacher's knowledge of the solution. We reverse the typical preference query selection method by having the teacher create ordered preference pairs, since a teacher who knows the target can choose more informative pairs than a learner choosing its own queries. Exploiting this advantage requires the teacher to model what the learner knows, and that model goes stale when the learner's belief changes in ways the teacher cannot see, as when several teachers each teach without knowing what the others taught. We call this teacher-model drift. In this work, we use second-order Theory-of-Mind (ToM-2) to have the learner create understanding statements that correct the teacher's model of the learner's knowledge. In simulation, we show that a learner with a perfect teacher, one with perfect knowledge of the learner, needs about half as many rounds as learner-guided querying to learn the reward. Yet when teacher-model drift is induced by alternating between four co-teachers, the advantage erodes. We tested two types of understanding statement generation: the learner's mean belief and ToM-2 drift minimization. ToM-2 statements reduced the drift and recovered more of the lost advantage than mean statements. In a within-subjects study (n = 101) with a simulated ideal co-teacher, ToM-2 statements raised the learner's final alignment with the true reward above both uninformed and mean-informed teaching; on the regret participants removed in their own rounds, they outperformed uninformed teaching but not mean statements.

作者备注:v2: substantially revised and extended version with a human-subject study. v1 appeared at the IROS 2026 Workshop on Leveraging Behavioral Models in Human-Autonomy Teams (BEMHAT)

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

本站首次收录为 v2,暂无更早版本可对照。

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。

v2 · 2026-11-16 12:38 · 最新观测版本

ToM-2 Understanding Statements for Teacher-Guided Preference Learning

Preference learning is a powerful tool for reward learning, but treats the teacher as a passive oracle that answers queries driven by the learner. This learner-guided query selection ignores the teacher's knowledge of the solution. We reverse the typical preference query selection method by having the teacher create ordered preference pairs, since a teacher who knows the target can choose more informative pairs than a learner choosing its own queries. Exploiting this advantage requires the teacher to model what the learner knows, and that model goes stale when the learner's belief changes in ways the teacher cannot see, as when several teachers each teach without knowing what the others taught. We call this teacher-model drift. In this work, we use second-order Theory-of-Mind (ToM-2) to have the learner create understanding statements that correct the teacher's model of the learner's knowledge. In simulation, we show that a learner with a perfect teacher, one with perfect knowledge of the learner, needs about half as many rounds as learner-guided querying to learn the reward. Yet when teacher-model drift is induced by alternating between four co-teachers, the advantage erodes. We tested two types of understanding statement generation: the learner's mean belief and ToM-2 drift minimization. ToM-2 statements reduced the drift and recovered more of the lost advantage than mean statements. In a within-subjects study (n = 101) with a simulated ideal co-teacher, ToM-2 statements raised the learner's final alignment with the true reward above both uninformed and mean-informed teaching; on the regret participants removed in their own rounds, they outperformed uninformed teaching but not mean statements.

查看此版本解读 →查看此版本原文 ↗