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 2402.09734cs.AI
收藏

智能体无需知晓其目的

Agents Need Not Know Their Purpose

International School of Engineering, Chulalongkorn University(朱拉隆功大学国际工程学院)

Paulo Garcia

AI总结:

本文提出遗忘型智能体架构,通过黑盒隐藏效用函数使智能体在理性最大化对齐时无需知晓真实目的,且对齐效果随智能提升而增强。

摘要:

确保人工智能以符合人类价值观的方式行为,通常被称为对齐挑战。先前的工作表明,理性智能体在最大化效用函数时,不可避免地会表现出与人类价值观不对齐的行为,尤其是随着其智能水平的提高。先前的工作还表明,不存在“唯一真实的效用函数”;解决方案必须包含更全面的对齐方法。本文描述了遗忘型智能体(oblivious agents):此类智能体的架构设计使其有效效用函数是已知子函数与隐藏子函数的聚合。待最大化的隐藏组件在内部以黑盒形式实现,阻止智能体对其进行检查。待最小化的已知组件是对隐藏子函数的认知。架构约束进一步影响智能体动作如何演化其内部环境模型。我们表明,遗忘型智能体在理性行为下,会构建设计者意图的内部近似(即推断对齐),并且作为其架构和有效效用函数的结果,其行为方式会最大化对齐;即最大化近似的意图函数。我们表明,矛盾的是,无论何种效用函数被用作隐藏组件,它都会做到这一点,并且与现有技术相比,随着智能体智能的增长,对齐的几率实际上会提高。

英文摘要:

Ensuring artificial intelligence behaves in such a way that is aligned with human values is commonly referred to as the alignment challenge. Prior work has shown that rational agents, behaving in such a way that maximizes a utility function, will inevitably behave in such a way that is not aligned with human values, especially as their level of intelligence goes up. Prior work has also shown that there is no "one true utility function"; solutions must include a more holistic approach to alignment. This paper describes oblivious agents: agents that are architected in such a way that their effective utility function is an aggregation of a known and hidden sub-functions. The hidden component, to be maximized, is internally implemented as a black box, preventing the agent from examining it. The known component, to be minimized, is knowledge of the hidden sub-function. Architectural constraints further influence how agent actions can evolve its internal environment model. We show that an oblivious agent, behaving rationally, constructs an internal approximation of designers' intentions (i.e., infers alignment), and, as a consequence of its architecture and effective utility function, behaves in such a way that maximizes alignment; i.e., maximizing the approximated intention function. We show that, paradoxically, it does this for whatever utility function is used as the hidden component and, in contrast with extant techniques, chances of alignment actually improve as agent intelligence grows.

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。

↑