arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.08552cs.AIcs.MAcs.NEphysics.data-an
收藏

定量承诺理论:自主智能体中的意向性与推理

Quantitative Promise Theory: Intentionality and Inference in Autonomous Agents

ChiTek-i AS

Mark Burgess

AI总结:

本文提出将贝叶斯概率与信息论优化(包括主动推理)融入承诺语义,以解决概率计算中的非局部协调、校准和归一化问题,并利用边界条件作为承诺约束状态与决策阈值,实现可扩展的意图定义。

摘要:

我讨论了涉及自主智能体过程的承诺理论的一些定量表示。智能体模型在软件系统、机器学习和生物学中很常见,但也可能适用于物理学和其他工程形式。我描述了贝叶斯概率和信息论优化(包括主动推理)如何与承诺语义相结合——以及承诺理论如何补充解决方案,帮助避免概率的陷阱,包括非局部协调、校准和归一化概率计算。边界条件在约束允许状态和选择决策阈值中的作用是一种承诺形式,而智能体对齐提供了意图的可扩展定义。自主智能体可以通过最小化其信息来凝聚成具有超级智能体特征的群体,尽管不确定性会最大化信息。承诺理论的使用涉及一些研究挑战以及风格偏好。

英文摘要:

I discuss some quantitative representations of Promise Theory for processes involving autonomous agents. Agent models are common in software systems, machine learning, and biology, for example, but may also apply to physics and other forms of engineering. I describe how Bayesian probability and information theoretic optimization, including Active Inference, may be incorporated with promise semantics -- as well as how Promise Theory supplements solutions, helping to avoid probability's pitfalls, which include non-local coordination, calibrating, and normalizing probabilistic computations. The role of boundary conditions in constraining allowed states and selecting decision thresholds is a form of promise, and agent alignment provides a scalable definition of intent. Autonomous agents may congeal into swarms with superagent characteristics by trying to minimize their information, despite uncertainty that works to maximize it. The use of Promise Theory involves some research challenges as well as stylistic preferences.

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。

↑