# How a minimal learning agent can infer the existence of unobserved variables in a complex environment

arXiv: https://arxiv.org/abs/1910.06985 · HTML: https://mlsanity.com/paper/1910.06985/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2019.

## Built on by (most cited first, 7 of 7)

- [Interpretable Machine Learning in Physics: A Review](https://mlsanity.com/paper/2503.23616/) (2025)
- [Towards interpretable quantum machine learning via single-photon quantum walks](https://mlsanity.com/paper/2301.13669/) (2023)
- [Free Energy Projective Simulation (FEPS): Active inference with interpretability](https://mlsanity.com/paper/2411.14991/) (2024)
- [Automated Gadget Discovery in Science](https://mlsanity.com/paper/2212.12743/) (2022)
- [Learning effective good variables from physical data](https://mlsanity.com/paper/2401.05226/) (2024)
- [Abstaining Machine Learning -- Philosophical Considerations](https://mlsanity.com/paper/2409.00706/) (2024)
- [Interpreting Quantum Learning Models via Stochastic Processes](https://mlsanity.com/paper/2607.17327/) (2026)

## Abstract (arXiv)

According to a mainstream position in contemporary cognitive science and philosophy, the use of abstract compositional concepts is both a necessary and a sufficient condition for the presence of genuine thought. In this article, we show how the ability to develop and utilise abstract conceptual structures can be achieved by a particular kind of learning agents. More specifically, we provide and motivate a concrete operational definition of what it means for these agents to be in possession of abstract concepts, before presenting an explicit example of a minimal architecture that supports this capability. We then proceed to demonstrate how the existence of abstract conceptual structures can be operationally useful in the process of employing previously acquired knowledge in the face of new experiences, thereby vindicating the natural conjecture that the cognitive functions of abstraction and generalisation are closely related. Keywords: concept formation, projective simulation, reinforcement learning, transparent artificial intelligence, theory formation, explainable artificial intelligence (XAI)