多智能体系统中的人类价值观（英文版）

英文标题：Human Values in Multiagent Systems中文摘要：本文提供一个源于社会科学、能够形式化表达价值的形式化表述，并使用此表述明确了实现 AI 价值对齐的关键挑战和研究路线图。英文摘要：One of the major challenges we face with ethical AI today is developingcomputational systems whose reasoning and behaviour are provably aligned withhuman values. Human values, however, are notorious for being ambiguous,contradictory and ever-changing. In order to bridge this gap, and get us closerto the situation where we can formally reason about implementing values intoAI, this paper pr