TL;DR本文旨在研究 AI 智能代理器对于陌生和新的因变量的预测和探索问题,提出了一种基于先前经验的较为有效的处理方法,并能够实现零样本预测。
Abstract
The ability of an agent to perform well in new and unseen environments is a
crucial aspect of intelligence. In machine learning, this ability is referred
to as strong or out-of-distribution generalization. However, simply considering
differences in data distributions is not sufficient to fully capture
differences in environments. In the present paper, we ass