English

Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning

Machine Learning 2025-12-30 v1 Artificial Intelligence Computer Vision and Pattern Recognition Neural and Evolutionary Computing Neurons and Cognition

Abstract

Predictive coding has emerged as a prominent model of how the brain learns through predictions, anticipating the importance accorded to predictive learning in recent AI architectures such as transformers. Here we propose a new framework for predictive coding called active predictive coding which can learn hierarchical world models and solve two radically different open problems in AI: (1) how do we learn compositional representations, e.g., part-whole hierarchies, for equivariant vision? and (2) how do we solve large-scale planning problems, which are hard for traditional reinforcement learning, by composing complex action sequences from primitive policies? Our approach exploits hypernetworks, self-supervised learning and reinforcement learning to learn hierarchical world models that combine task-invariant state transition networks and task-dependent policy networks at multiple abstraction levels. We demonstrate the viability of our approach on a variety of vision datasets (MNIST, FashionMNIST, Omniglot) as well as on a scalable hierarchical planning problem. Our results represent, to our knowledge, the first demonstration of a unified solution to the part-whole learning problem posed by Hinton, the nested reference frames problem posed by Hawkins, and the integrated state-action hierarchy learning problem in reinforcement learning.

Keywords

Cite

@article{arxiv.2210.13461,
  title  = {Active Predictive Coding: A Unified Neural Framework for Learning Hierarchical World Models for Perception and Planning},
  author = {Rajesh P. N. Rao and Dimitrios C. Gklezakos and Vishwas Sathish},
  journal= {arXiv preprint arXiv:2210.13461},
  year   = {2025}
}

Comments

15 pages, 10 figures, 2 supplementary figures

R2 v1 2026-06-28T04:23:24.168Z