提出代理性依赖于参照系，改变视角会改变对系统是否具备自主性的判断。
Agency Is Frame-Dependent
- 从强化学习视角论证代理性本质是参照系依赖的
- 证明代理性的核心属性均依赖于观察框架
- 为智能系统评估提供新范式，适合研究智能与认知的学者
代理性是指系统朝目标引导结果的能力，是生物学、哲学、认知科学和人工智能中的核心议题。判断一个系统是否具备代理性是一个长期难题：例如，丹内特（1989）指出，难以确定一块石头、一个恒温器或一台机器人是否具有代理性。本文从强化学习角度出发，主张代理性本质上是参照系依赖的——任何对系统代理性的测量都必须相对于某一参照框架进行。我们通过哲学论证表明，Barandiaran 等人（2009）和 Moreno（2018）提出的代理性核心属性本身也具有参照系依赖性。由此得出结论：任何关于代理性的基础科学都必须承认其框架依赖性，并讨论该观点对强化学习的深远影响。
原文摘要 · Abstract (English)
Agency is a system's capacity to steer outcomes toward a goal, and is a central topic of study across biology, philosophy, cognitive science, and artificial intelligence. Determining if a system exhibits agency is a notoriously difficult question: Dennett (1989), for instance, highlights the puzzle of determining which principles can decide whether a rock, a thermostat, or a robot each possess agency. We here address this puzzle from the viewpoint of reinforcement learning by arguing that agency is fundamentally frame-dependent: Any measurement of a system's agency must be made relative to a reference frame. We support this claim by presenting a philosophical argument that each of the essential properties of agency proposed by Barandiaran et al. (2009) and Moreno (2018) are themselves frame-dependent. We conclude that any basic science of agency requires frame-dependence, and discuss the implications of this claim for reinforcement learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。