# Curiosity-driven Intuitive Physics Learning

arXiv: https://arxiv.org/abs/2105.07426 · HTML: https://mlsanity.com/paper/2105.07426/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 16 May 2021.

## Builds on (most cited first, 7 of 7)

- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning](https://mlsanity.com/paper/1803.07616/) (2018)
- [Watch, Try, Learn: Meta-Learning from Demonstrations and Reward](https://mlsanity.com/paper/1906.03352/) (2019)
- [Learning Quickly to Plan Quickly Using Modular Meta-Learning](https://mlsanity.com/paper/1809.07878/) (2018)
- [Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos](https://mlsanity.com/paper/2006.00545/) (2020)
- [Online Learning of a Memory for Learning Rates](https://mlsanity.com/paper/1709.06709/) (2017)

## Abstract (arXiv)

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.