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.
View on arXiv@article{abel2025_2502.04403,
title={ Agency Is Frame-Dependent },
author={ David Abel and André Barreto and Michael Bowling and Will Dabney and Shi Dong and Steven Hansen and Anna Harutyunyan and Khimya Khetarpal and Clare Lyle and Razvan Pascanu and Georgios Piliouras and Doina Precup and Jonathan Richens and Mark Rowland and Tom Schaul and Satinder Singh },
journal={arXiv preprint arXiv:2502.04403},
year={ 2025 }
}