cs.AINov 9, 2026

Building World Models from Intrinsic Motivation

Authors: Reece Keller, Declan Kutscher, Xaq Pitkow, Aran Nayebi

Organizations: Neuroscience Institute, Carnegie Mellon University · Robotics Institute, Carnegie Mellon University · Department of Computer Science, University of Maryland, College Park · Machine Learning Department, Carnegie Mellon University

Abstract

In the absence of extrinsic rewards or task supervision, human behavior is guided by intrinsic motivation---neural signals that drive curiosity, creativity, play, and other essential facets of intelligence. Intrinsic motivation plays an important developmental role in building robust world models that enable generalization and adaptation. Yet existing studies leave open how a broad range of intrinsic motivations interacts with world-model representation learning to support downstream control. This limits our understanding of which intrinsically collected experiences build reusable models. To address these gaps, we integrate 24 intrinsic objectives, including established methods and explicit variants spanning curiosity, entropy, and competency, into a common model-based reinforcement learning framework. We evaluate the world models they build through zero-shot, few-shot, and multi-task control in locomotion, manipulation, and open-ended gaming environments, using three representation-learning strategies: observation reconstruction, latent prediction, and redundancy reduction. Curiosity-driven exploration with observation reconstruction yields the strongest aggregate family profile, although the best individual pairing depends on the experiment. In compositional vision-based tasks, intrinsic motivation derived from both episodic and lifelong novelty---providing a complementary memory to the world model's generic recurrent state---achieves the best zero-shot transfer and few-shot adaptation. These findings motivate designing intrinsic motivation and representation learning jointly. Our results demonstrate world models as a powerful tool for measuring the quality of intrinsically motivated experience, and positions intrinsic motivation as a key ingredient for building world models autonomously.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Human Cognition in Machines: A Unified Perspective of World Models

    Apr 17, 2026Timothy Rupprecht, Pu Zhao, Amir Taherin +20Computational Cognitive ModelingWorld Model Learning

  2. Towards Zero-Shot Task Transfer with Neurosymbolic World Models

    Aug 18, 2026Isidoro Tamassia, Lennert De Smet, Giuseppe MarraZero-Shot RLWorld Model Learning