From pixels to planning: scale-free active inference

From pixels to planning: scale-free active inference

This paper describes a discrete state-space model and accompanying methods for generative modeling. This model generalizes partially observed Markov decision processes to include paths as latent variables, rendering it suitable for active inference and learning in a dynamic setting. Specifically, we...

Full description

Saved in:
Bibliographic Details
Main Authors: Karl Friston, Conor Heins, Tim Verbelen, Lancelot Da Costa, Tommaso Salvatori, Dimitrije Markovic, Alexander Tschantz, Magnus Koudahl, Christopher Buckley, Thomas Parr
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Network Physiology
Subjects:
active inference
active learning
Bayesian model selection
renormalization group
compression
structure learning
Online Access:https://www.frontiersin.org/articles/10.3389/fnetp.2025.1521963/full
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items

Similar Items