arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.02739cs.AIcs.CYcs.MA
收藏

多智能体系统中的人类价值观

Human Values in Multiagent Systems

Artificial Intelligence Research Institute (IIIA-CSIC)(人工智能研究所(IIIA-CSIC));Goldsmiths, University of London(伦敦大学金史密斯学院)

Nardine Osman, Mark d'Inverno

AI总结:

针对人类价值观模糊矛盾且动态变化、难以实现AI价值对齐的问题,本文提出基于社会科学的价值观形式化表示方法,明确了多智能体系统价值对齐的核心挑战并给出研究路线图。

摘要:

当前伦理AI领域面临的核心挑战之一,是构建推理与行为可证明符合人类价值观的计算系统。但人类价值观素来以模糊性、矛盾性和动态变化著称。为弥合这一鸿沟,推动实现可对AI中的价值观植入开展形式化推理的目标,本文提出了一种基于社会科学的价值观形式化表示方法。我们利用该形式化表示,阐明了在多智能体系统(MAS)中实现价值对齐行为的关键挑战,并提出了应对这些挑战的研究路线图。

英文摘要:

One of the major challenges we face with ethical AI today is developing computational systems whose reasoning and behaviour are provably aligned with human values. Human values, however, are notorious for being ambiguous, contradictory and ever-changing. In order to bridge this gap, and get us closer to the situation where we can formally reason about implementing values into AI, this paper presents a formal representation of values, grounded in the social sciences. We use this formal representation to articulate the key challenges for achieving value-aligned behaviour in multiagent systems (MAS) and a research roadmap for addressing them.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑