跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2602.09490 · v3

Robust Trust

首次提交 2026-02-10 15:39
版本更新 2026-11-14 16:46
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

An agent chooses an action based on her private information and a recommendation from an informed but potentially misaligned adviser. With a known probability, the adviser truthfully reports his signal; with the remaining probability, he can send any message. We characterize robustly optimal decision rules that maximize the agent's worst-case expected payoff. Every optimal rule is equivalent to a trust-region policy in belief space: the adviser's reported beliefs are taken at face value if they fall within the trust region but are otherwise projected onto the trust region's boundary. We derive alignment thresholds above which advice is strictly valuable, explicitly characterize the solution in binary-state environments, and develop a procedure for computing the trust region numerically.

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 v3,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。

v3 · 2026-11-14 16:46 · 最新观测版本

Robust Trust

An agent chooses an action based on her private information and a recommendation from an informed but potentially misaligned adviser. With a known probability, the adviser truthfully reports his signal; with the remaining probability, he can send any message. We characterize robustly optimal decision rules that maximize the agent's worst-case expected payoff. Every optimal rule is equivalent to a trust-region policy in belief space: the adviser's reported beliefs are taken at face value if they fall within the trust region but are otherwise projected onto the trust region's boundary. We derive alignment thresholds above which advice is strictly valuable, explicitly characterize the solution in binary-state environments, and develop a procedure for computing the trust region numerically.

查看此版本解读 →查看此版本原文 ↗