.png){kind=icon}
.png){kind=icon}
Return
Active inference and artificial reasoning
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-026-77209-5.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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. Humans are remarkably adept at learning from sparse data, in part because they selectively sample information that is most informative about the rules governing their environment. Here, the authors demonstrate that uncertainty about the structure of one's internal model can be used to guide behavior, facilitating the efficient discovery of hidden rules.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
15.7
Papers:
9.3W
Citations:
91.2W
Organization
View more organizations