arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.08759cs.AIcs.MA
收藏

自主智能体的价值工程

Value Engineering for Autonomous Agents

Artificial Intelligence Research Institute (IIIA-CSIC)(人工智能研究院(IIIA-CSIC));University of Bergen(卑尔根大学)

Nieves Montes, Nardine Osman, Carles Sierra, Marija Slavkovik

摘要:

机器伦理学(ME)关注人工道德代理(AMA)的设计,即能够根据道德价值进行推理和行为的自主智能体。以前的方法将值视为与世界的某些动作或状态相关联的标签,而不是作为Agent推理的组成部分。人们也常常忽视,一个价值导向的代理人与其他价值导向的代理人一起在规范管理的环境中运作,从而忽略了AMA的社会维度。在这篇蓝天论文中,我们提出了一个新的AMA范式,它基于道德和社会心理学,将价值观作为依赖于上下文的目标灌输给代理人。这些目标通过评估现有规范最激励的结果,将个人层面的价值观与集体层面的规范紧密联系起来。我们认为,这种类型的规范性推理,其中代理人被赋予与规范的道德含义的理解,导致价值意识的自主智能体。此外,这种能力为代理人铺平了道路,使其社会中实施的规范与灌输给他们的人类价值观保持一致,通过协议机制补充基于价值的规范推理,以帮助代理人集体商定适合其人类价值观的最佳规范。总的来说,我们的代理模型超越了将价值观作为惰性标签的处理,将它们与规范推理和将价值感知代理集成到现代混合人机社会所需的社会功能相连接。

英文摘要:

Machine Ethics (ME) is concerned with the design of Artificial Moral Agents (AMAs), i.e. autonomous agents capable of reasoning and behaving according to moral values. Previous approaches have treated values as labels associated with some actions or states of the world, rather than as integral components of agent reasoning. It is also common to disregard that a value-guided agent operates alongside other value-guided agents in an environment governed by norms, thus omitting the social dimension of AMAs. In this blue sky paper, we propose a new AMA paradigm grounded in moral and social psychology, where values are instilled into agents as context-dependent goals. These goals intricately connect values at individual levels to norms at a collective level by evaluating the outcomes most incentivized by the norms in place. We argue that this type of normative reasoning, where agents are endowed with an understanding of norms' moral implications, leads to value-awareness in autonomous agents. Additionally, this capability paves the way for agents to align the norms enforced in their societies with respect to the human values instilled in them, by complementing the value-based reasoning on norms with agreement mechanisms to help agents collectively agree on the best set of norms that suit their human values. Overall, our agent model goes beyond the treatment of values as inert labels by connecting them to normative reasoning and to the social functionalities needed to integrate value-aware agents into our modern hybrid human-computer societies.

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。

↑