This paper considers the sampling of outcomes that provide the greatest amount of information about the structure of underlying world models. This generalisation furnishes a principled approach to structure learning, and specifically rule discovery, under a plausible set of generative models or hypotheses. In active inference, policies—i.e., combinations of actions—are selected based on their expected free energy, which comprises expected information gain and value.
Information gain corresponds to the Kullback-Leibler divergence between predictive posteriors with, and without, the consequences of action. Posteriors over models can be evaluated quickly and efficiently using Bayesian Model Reduction, based upon accumulated posterior beliefs about model parameters. The ensuing information gain can then be used to select actions that disambiguate among alternative models, in the spirit of optimal experimental design.
We illustrate this kind of active selection or reasoning using partially observed discrete models; namely, a three-ball paradigm used previously to describe artificial insight and aha moments via (synthetic) introspection or sleep. We focus on the sample efficiency afforded by seeking outcomes that resolve the greatest uncertainty about the world model, under which outcomes are generated. KF discloses support for the research of this work from Wellcome Trust (Ref: 226793/Z/22/Z).
TP discloses support for the research of this work from NIHR [Academic Clinical Fellowship (ref: ACF-2023-13-013)]. Queen Square Institute of Neurology, University College London, London, UK Karl Friston, Lancelot Da Costa, Alexander Tschantz, Christopher L. Buckley & Tim Verbelen ELLIS Institute Tübingen, Tübingen, Germany Department of Informatics, University of Sussex, Brighton, UK Alexander Tschantz & Christopher L.
Buckley Max Planck Institute of Animal Behavior, Department of Collective Behaviour, Konstanz, Germany Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK The authors declare no competing interests. Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.
The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Extract — continue reading at the source.
