Modeling Agents from the Perspective of Human Umwelt towards AI Safety

Abstract

Transparency in machine learning (ML) agents’ decision making is crucial for achieving AI Safety. However, it is difficult to comprehend agents’ behavior because gaps of perception, mobility, desire, and time scale between humans and ML agents obstruct people to mentalize the agents. In this paper, we propose a model of human’s inference of ML agents’ mental states so as to explain the agents’ behavior from the perspective of humans.