Curiosity-driven Intuitive Physics Learning
This work addresses the challenge of building more human-like, adaptive AI agents capable of understanding physical environments, though it appears incremental as it builds on existing curiosity-driven and physics learning approaches.
The paper tackles the problem of enabling AI agents to learn intuitive physics from scratch by proposing a curiosity-driven model based on discontinuities in fundamental physical parameters like shape constancy and object permanence, with the result being a framework that supports learning and inference across domains without specifying concrete performance metrics.
Biological infants are naturally curious and try to comprehend their physical surroundings by interacting, in myriad multisensory ways, with different objects - primarily macroscopic solid objects - around them. Through their various interactions, they build hypotheses and predictions, and eventually learn, infer and understand the nature of the physical characteristics and behavior of these objects. Inspired thus, we propose a model for curiosity-driven learning and inference for real-world AI agents. This model is based on the arousal of curiosity, deriving from observations along discontinuities in the fundamental macroscopic solid-body physics parameters, i.e., shape constancy, spatial-temporal continuity, and object permanence. We use the term body-budget to represent the perceived fundamental properties of solid objects. The model aims to support the emulation of learning from scratch followed by substantiation through experience, irrespective of domain, in real-world AI agents.