[3J1] [General Session] 7. Agent

[3J1-05] Modeling Agents from the Perspective of Human Umwelt towards AI Safety

〇Yosuke Fukuchi¹, Masahiko Osawa^1,2, Hiroshi Yamakawa^3,4, Michita Imai¹ (1. Graduate School of Science and Technology, Keio University, 2. Research Fellow of Japan Society for the Promotion of Science (DC1), 3. DWANGO Co., ltd Dwango Artificial Intelligence Laboratory, 4. The Whole Brain Architecture Initiative)

Keywords:AI Safety, Human-Agent Interaction, Umwelt

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.