A "good regulator theorem" for embodied agents

• URL: http://arxiv.org/abs/2508.06326v2
• Date: Thu, 21 Aug 2025 16:17:58 GMT
• Title: A "good regulator theorem" for embodied agents
• Abstract summary: Conant and Ashby claimed that "every good regulator of a system must be a model of that system"<n>Here we show that a similar intuition can be fleshed out in a different way.<n>It is possible for an observer to interpret it as having "beliefs" about its environment.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In a classic paper, Conant and Ashby claimed that "every good regulator of a system must be a model of that system." Artificial Life has produced many examples of systems that perform tasks with apparently no model in sight; these suggest Conant and Ashby's theorem doesn't easily generalise beyond its restricted setup. Nevertheless, here we show that a similar intuition can be fleshed out in a different way: whenever an agent is able to perform a regulation task, it is possible for an observer to interpret it as having "beliefs" about its environment, which it "updates" in response to sensory input. This notion of belief updating provides a notion of model that is more sophisticated than Conant and Ashby's, as well as a theorem that is more broadly applicable. However, it necessitates a change in perspective, in that the observer plays an essential role in the theory: models are not a mere property of the system but are imposed on it from outside. Our theorem holds regardless of whether the system is regulating its environment in a classic control theory setup, or whether it's regulating its own internal state; the model is of its environment either way. The model might be trivial, however, and this is how the apparent counterexamples are resolved.

Related papers

• Ontic and epistemic states in the theory of spacetime-local beables [0.0]
  Bell's theorem rules out developing a locally causal theory to describe quantum phenomena.<n>Many take this to imply that any model of quantum entanglement must employ variables (called beables by Bell) which follow nonlocal rules.<n>The alternative is to adopt an all-at-once (block universe) approach, with beables which may depend on both past and future inputs.
  arXiv  Detail & Related papers  (2026-09-01T07:46:23Z)
• A game theory for foundation models shows new paths to rational cooperation through similarity inference [56.53805518668248]
  We show that foundation model agents engaging in optimal planning consistently converge to stable cooperation.<n>By shifting from decoupled to embedded agency, these agents model themselves as part of the universe they inhabit.
  arXiv  Detail & Related papers  (2026-08-04T17:24:33Z)
• What Syntax Cannot See: The Dynamic Syntactic Invariance Principle and Several Instances of the Same Hidden Assumption, and a Contradiction [0.0]
  This paper develops a single method, find what an accepted result silently assumed, make it a variable, and prove what follows once it is dropped.<n>It shows it keeps working across domains with nothing in common.
  arXiv  Detail & Related papers  (2026-08-02T03:10:44Z)
• World models of environment, agent and joint agent-environment systems [76.81951414842736]
  We argue that there is a prior distinction: which channel they model.<n>We consider three cases: the environment channel $O_: mid A_:$, the agent channel $A_: mid O_:$, and the realised joint process $(A, O)_:$, equivalently viewed as a channel with no inputs.
  arXiv  Detail & Related papers  (2026-07-23T13:35:03Z)
• Reliability, Faithfulness, and the Limits of Post-hoc Explanations of Opaque Scientific Models [0.6875312133832079]
  Post-hoc explanation methods are routinely used to interpret scientific machine learning models.<n>We argue that the transition may be taken to be secured once the model is reliable enough and the explanation faithful enough.<n> Reliability checks that the model's predictions match the phenomenon's outcomes, and faithfulness checks that the explanation matches the model, but neither checks whether the model works as the phenomenon works.
  arXiv  Detail & Related papers  (2026-06-28T11:29:15Z)
• Conditioning Accept-Desirability models in the context of AGM-like belief change [0.0]
  We discuss conditionalisation for Accept-Desirability models in an abstract decision-making framework.<n>We introduce a new conditioning rule for our Accept-Desirability models, based on the idea that observing an event introduces new indifferences between options.<n>We investigate two interesting special cases where all of these axioms are shown to still hold: classical propositional logic and full conditional probabilities.
  arXiv  Detail & Related papers  (2025-12-22T07:07:34Z)
• Newton to Einstein: Axiom-Based Discovery via Game Design [55.30047000068118]
  We propose a game design framework in which scientific inquiry is recast as a rule-evolving system.<n>Unlike conventional ML approaches that operate within fixed assumptions, our method enables the discovery of new theoretical structures.
  arXiv  Detail & Related papers  (2025-09-05T18:59:18Z)
• Diagrammatic Reasoning with Control as a Constructor, Applications to Quantum Circuits [0.0]
  We introduce a general framework for diagrammatic reasoning featuring control as a constructor.<n>We show that controlled props ease diagrammatic reasoning for quantum circuits by allowing a simple complete set of relations.
  arXiv  Detail & Related papers  (2025-08-29T16:34:00Z)
• Opacity as Authority: Arbitrariness and the Preclusion of Contestation [0.0]
  Article redefines arbitrariness not as a normative flaw or a symptom of domination, but as a functional mechanism structuring human systems and interactions.<n>Building on Ferdinand de Saussure's concept of l'arbitraire du signe, the analysis extends this principle beyond language to demonstrate its cross-domain applicability.
  arXiv  Detail & Related papers  (2025-07-25T19:10:35Z)
• Are language models rational? The case of coherence norms and belief revision [63.78798769882708]
  We consider logical coherence norms as well as coherence norms tied to the strength of belief in language models. We argue that rational norms tied to coherence do apply to some language models, but not to others.
  arXiv  Detail & Related papers  (2024-06-05T16:36:21Z)
• Logic meets Wigner's Friend (and their Friends) [49.1574468325115]
  We take a fresh look at Wigner's Friend thought-experiment and some of its more recent variants and extensions. We discuss various solutions proposed in the literature, focusing on a few questions.
  arXiv  Detail & Related papers  (2023-07-04T13:31:56Z)
• Deep Grey-Box Modeling With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models [88.63781315038824]
  We present a framework that enables us to analyze a regularizer's behavior empirically with a slight change in the neural net's architecture and the training objective.
  arXiv  Detail & Related papers  (2022-10-24T10:42:26Z)
• A "thoughtful" Local Friendliness no-go theorem: a prospective experiment with new assumptions to suit [0.0]
  We present a new LF no-go theorem which takes seriously the idea that a system's having *thoughts* is a sufficient condition for it to be an observer. In addition to these four metaphysical assumptions, this new no-go theorem requires two assumptions about what is *technologically* feasible.
  arXiv  Detail & Related papers  (2022-09-18T07:11:23Z)
• Observing Interventions: A logic for thinking about experiments [62.997667081978825]
  This paper makes a first step towards a logic of learning from experiments. Crucial for our approach is the idea that the notion of an intervention can be used as a formal expression of a (real or hypothetical) experiment. For all the proposed logical systems, we provide a sound and complete axiomatization.
  arXiv  Detail & Related papers  (2021-11-25T09:26:45Z)
• Explicit construction of Local Hidden Variables for any quantum theory up to any desired accuracy [0.0]
  The machinery of quantum mechanics is fully capable of describing a single realistic world. Bell's theorem is not applicable in the cases considered. The potential importance of our construction in model building is discussed.
  arXiv  Detail & Related papers  (2021-03-07T12:19:57Z)
• Observers of quantum systems cannot agree to disagree [55.41644538483948]
  We ask whether agreement between observers can serve as a physical principle that must hold for any theory of the world. We construct examples of (postquantum) no-signaling boxes where observers can agree to disagree.
  arXiv  Detail & Related papers  (2021-02-17T19:00:04Z)
• Autonomous Quantum Devices: When Are They Realizable without Additional Thermodynamic Costs? [0.13844779265721088]
  unitary operations have been considered a "free" resource in the quantum thermodynamics theory. Here, we include an auxiliary control system which can autonomously implement the unitary by turning an interaction "on or off" We derive conditions on the quality of the control device so that the laws of thermodynamics do not change and prove - by utilizing a good quantum clock - that the laws of quantum mechanics allow the backreaction to be small enough so that these conditions are satisfiable.
  arXiv  Detail & Related papers  (2019-12-11T19:00:09Z)
• A Unified Scientific Basis for Inference [0.0]
  It is shown that a natural extension of this discussion gives a conceptual basis from which essential parts of the formalism of quantum mechanics can be derived. The questions around Bell's inequality are approached by using the conditionality principle for each observer.
  arXiv  Detail & Related papers  (2012-06-22T07:34:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.