The Fragility of Social Learning with Noisy Messages

2026-08-18

AI Summary

研究探讨了在信息经过噪声传递后，代理如何学习。只有当代理能够接触到足够多的噪声传递链并且完全理解噪声过程时，才能成功学习。

Abstract

We examine how agents learn when information from original sources only reaches them after noisy relay. A receiver learns if and only if they have access to sufficiently many chains of noisy relay and they perfectly understand the noise process. However, even slight uncertainty over message mutation rates makes learning from long chains impossible, no matter how many independent sources are accessed.

Problem

• noisy relay
• social learning
• message mutation rates

Innovation

• noisy relay
• social learning
• message mutation rates