BriefGPT.xyz
Apr, 2024
自适应采样策略暗示有偏信念：热炉效应的推广
Adaptive Sampling Policies Imply Biased Beliefs: A Generalization of the Hot Stove Effect
HTML
PDF
Jerker Denrell
TL;DR
研究旨在解释学习过程中的负性偏差现象，并表明这种负性偏差在特定设置下仍然存在，同时也存在贝叶斯学习者对替代方案预期值的低估现象。
Abstract
The
hot stove effect
is a
negativity bias
resulting from the adaptive character of learning. The mechanism is that
learning algorithms
tha
→