BriefGPT.xyz
Oct, 2024
多价值战略环境中的责任
Responsibility in a Multi-Value Strategic Setting
HTML
PDF
Timothy Parker, Umberto Grandi, Emiliano Lorini
TL;DR
本研究旨在解决多智能体系统中责任归属的问题，尤其是在考虑多重结果的背景下。提出了一种新的责任归属模型，并扩展至责任预期，展示了如何通过责任的考量来指导智能体选择符合其价值观的战略。研究发现，非主导的遗憾最小化策略能够可靠地降低智能体的预期责任程度。
Abstract
Responsibility
is a key notion in
Multi-agent systems
and in creating safe, reliable and
Ethical AI
. However, most previous work on
→