A Triviality Worry for the Internal Model Principle

Synthese 204 (1):1-16 (2024)
  Copy   BIBTEX

Abstract

The Good Regulator Theorem and the Internal Model Principle are sometimes cited as mathematical proofs that an agent needs an internal model of the world in order to have an optimal policy. However, these principles rely on a definition of “internal model" that is far too permissive, applying even to cases of systems that do not use an internal model. As a result, these principles do not provide evidence (let alone a proof) that internal models are necessary. The paper also diagnoses what is missing in the GRT and IMP definitions of internal model, which is that models need to make predictions that represent variables in the target system (and these representations need to be usable by an agent so as to guide behavior).

Other Versions

No versions found

Similar books and articles

The evolution of cognition—a hypothesis.Holk Cruse - 2003 - Cognitive Science 27 (1):135-155.
Mathematical Internal Realism.Tim Button - 2022 - In Sanjit Chakraborty & James Ferguson Conant, Engaging Putnam. Berlin, Germany: De Gruyter. pp. 157-182.
Resplendent models and $${\Sigma_1^1}$$ -definability with an oracle.Andrey Bovykin - 2008 - Archive for Mathematical Logic 47 (6):607-623.
Sound Advice and Internal Reasons.Ariela Tubert - 2016 - Pacific Philosophical Quarterly 97 (2):181-199.
Models and representation.Richard Hughes - 1997 - Philosophy of Science 64 (4):336.
A strongly embodied approach to machine consciousness.Owen Holland - 2007 - Journal of Consciousness Studies 14 (7):97-110.
Internal models and spatial orientation.Daniel M. Merfeld - 2004 - Behavioral and Brain Sciences 27 (3):410-410.

Analytics

Added to PP
2024-06-28

Downloads
277 (#101,591)

6 months
163 (#26,470)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Imran Thobani
Stanford University

Citations of this work

No citations found.

Add more citations