nucleation

LIT-911: Agents and Devices: A Relative Definition of Agency

1 min read

Properties5
StatusActive — read in full 2026-10-11 (NOTE-705) from the arXiv PDF (v1). Worth reading as the cleanest formal version of Dennett's intentional stance: whether a system is an agent or a device is a Bayesian model comparison between a mixture of goal-optimizing descriptions (inverse RL) and a mixture of input-output mappings, made by an observer with a prior. It presupposes an identified system, and its results depend on the prior chosen.
Tagsagency, model-comparison, anthology-candidate
SupportsCLAIM-168 — Identifying agents by their will-organization is circular: will-organization is defined for an agent already given, and the agent-versus-device comparison presupposes an identified system, so neither can produce the factorization it is meant to find, CLAIM-174 — A candidate factor is an agent at a level when it is one system there, when a goal-directed description beats a device description by more than the Occam cost, and when its policy would adapt if its actions' consequences changed; it is a willed agent when, further, a will-organization over several regimes describes it better than none, and what passes that is the jurisdiction of a will-organization
Cited as “paper” byNOTE-705 — Orseau, McGill & Legg — Agents and Devices
Cited as “source” byTHEORY-1236 — Agency is relative to an observer: an identified system is an agent, for that observer, to the degree that a description of the function it optimises explains its behaviour better under the observer's prior than any description of its input-output mapping, THEORY-624 — Orseau, McGill and Legg cast whether an identified system is an agent or a device as Bayesian model comparison between descriptions of the function it optimises and descriptions of its input-output mapping, so that the verdict is relative to the observer's prior; on seven toy gridworld trajectories goal-seeking comes out agent-like and wall-following device-like, and they argue that under a speed prior everything may look like an agent

Graph View

Laurent Orseau, Simon McGregor McGill and Shane Legg (2018) — ARXIV-1805.12387

Key takeaways

Read in full; see NOTE-705.

  • Two stances, formalized. “‘devices’ are directly described in terms of an input-output mapping, while ‘agents’ are described in terms of the function they optimise”.
  • Relative. The question “is observer-relative, since it depends the observer’s prior knowledge”.
  • The thermostat is on the knife edge. Its two descriptions are “of comparable simplicity”.

Standing in the record

Filed on 2026-10-11 as the model-comparison half of the admission test for agents (CLAIM-174), and as a source for the circularity objection (CLAIM-168). It presupposes the identified system that the owner’s factorization would supply. Tags: agency first; model-comparison for the Bayesian agent-versus-device test. anthology-candidate comes last (ADR-005): the anthology’s agents-and-environments topic could hold it for its RL framing. It is read here for what makes a factor of a person, a couple or a firm an agent. Not held in the anthology.

Backlinks