.png){kind=icon}
返回
Human-aligned artificial intelligence is a multiobjective problem
.png){kind=icon}
OA
AI
DOI：10.1007/s10676-017-9440-6.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As the capabilities of artificial intelligence (AI) systems improve, it becomes important to constrain their actions to ensure their behaviour remains beneficial to humanity. A variety of ethical, legal and safety-based frameworks have been proposed as a basis for designing these constraints. Despite their variations, these frameworks share the common characteristic that decision-making must consider multiple potentially conflicting factors. We demonstrate that these alignment frameworks can be represented as utility functions, but that the widely used Maximum Expected Utility (MEU) paradigm provides insufficient support for such multiobjective decision-making. We show that a Multiobjective Maximum Expected Utility paradigm based on the combination of vector utilities and non-linear action-selection can overcome many of the issues which limit MEU's effectiveness in implementing aligned AI. We examine existing approaches to multiobjective AI, and identify how these can contribute to the development of human-aligned intelligent agents.
Keyword:
Ethics
Aligned artificial intelligence
Value alignment
Maximum Expected Utility
Reward engineering
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4
论文数:
742
被引数:
2.6K
机构
引用论文
分享收藏分享收藏分享收藏Unlocking the Entrepreneurial State of Mind for Digital Decade: SMEs and Digital Marketing.png)
Electronics
OAAI
ElectronicsIF0
OAAI分享收藏分享收藏Communicating Epistemic Stance: How Speech and Gesture Patterns Reflect Epistemicity and Evidentiality沟通认识论立场: 言语和手势模式如何反映认识论和证据OAAI
OAAI分享收藏
查看更多内容