Agency Is Frame-Dependent
🤖 AI Summary
This paper addresses the problem of determining system agency, challenging the assumption that agency is an absolute, intrinsic property. It argues instead that agency is fundamentally frame-dependent—i.e., inherently relative to a specific observational perspective or modeling framework—and cannot be defined or measured independently thereof. Methodologically, the work integrates philosophical analysis, conceptual modeling, and reinforcement learning theory, while critically re-examining Barandiaran and Moreno’s canonical criteria for agency. Through systematic demonstration, it shows that all key features of agency emerge only within—and are constitutively shaped by—a given reference frame. The study establishes frame-dependence as a foundational principle of agency, thereby providing both a novel philosophical and formal foundation for the science of agency and catalyzing paradigm shifts in reinforcement learning: specifically, in agent modeling, evaluation of goal-directedness, and ethical AI design.
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
Agency measurement is frame-dependent.
Determining system agency is complex.
Frame-dependence essential for agency science.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Frame-dependent agency measurement
Reinforcement learning perspective
Philosophical argument support
🔎 Similar Papers
