World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child
Preprint
Abstract
World Models help Artificial Intelligence (AI) predict outcomes, reason about its environment, and guide decision-making. While widely used in reinforcement learning, they lack the structured, adaptive representations that even young children intuitively develop. Advancing beyond pattern recognition requires dynamic, interpretable frameworks inspired by Piaget's cognitive development theory. We highlight six key research areas -- physics-informed learning, neurosymbolic learning, continual learning, causal inference, human-in-the-loop AI, and responsible AI -- as essential for enabling true reasoning in AI. By integrating statistical learning with advances in these areas, AI can evolve from pattern recognition to genuine understanding, adaptation and reasoning capabilities.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Challenges, evaluation and opportunities for open-world learningNature Machine Intelligence, 2024
- Managing the unknown in machine learning: Definitions, related areas, recent advances, and prospectsNeurocomputing, 2024
- Managing extreme AI risks amid rapid progressScience, 2024
- A Comprehensive Survey of Continual Learning: Theory, Method and ApplicationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulationInformation Fusion, 2023
- Neurosymbolic AI: the 3rd waveArtificial Intelligence Review, 2023
- A Survey of Embodied AI: From Simulators to Research TasksIEEE Transactions on Emerging Topics in Computational Intelligence, 2022
- Methods and tools for causal discovery and causal inferenceWIREs Data Mining and Knowledge Discovery, 2022
- How to Grow a Mind: Statistics, Structure, and AbstractionScience, 2011
- A Theory of Causal Learning in Children: Causal Maps and Bayes Nets.Psychological Review, 2004