# ToyArchitecture: Unsupervised Learning of Interpretable Models of the World

## TL;DR

This paper introduces a simple, interpretable hierarchical AI architecture that combines unsupervised learning, action modeling, reinforcement learning, planning, and symbolic integration, aiming for practical, understandable models of the world.

## Contribution

It presents a novel hierarchical architecture that unifies multiple AI mechanisms into an interpretable, unsupervised learning system with symbolic and sub-symbolic representations.

## Key findings

- Hierarchical representations are increasingly abstract yet retain details.
- The architecture supports symbolic and sub-symbolic interpretation at all levels.
- It enables efficient learning and inference combining symbolic and sub-symbolic methods.

## Abstract

Research in Artificial Intelligence (AI) has focused mostly on two extremes: either on small improvements in narrow AI domains, or on universal theoretical frameworks which are usually uncomputable, incompatible with theories of biological intelligence, or lack practical implementations. The goal of this work is to combine the main advantages of the two: to follow a big picture view, while providing a particular theory and its implementation. In contrast with purely theoretical approaches, the resulting architecture should be usable in realistic settings, but also form the core of a framework containing all the basic mechanisms, into which it should be easier to integrate additional required functionality. In this paper, we present a novel, purposely simple, and interpretable hierarchical architecture which combines multiple different mechanisms into one system: unsupervised learning of a model of the world, learning the influence of one's own actions on the world, model-based reinforcement learning, hierarchical planning and plan execution, and symbolic/sub-symbolic integration in general. The learned model is stored in the form of hierarchical representations with the following properties: 1) they are increasingly more abstract, but can retain details when needed, and 2) they are easy to manipulate in their local and symbolic-like form, thus also allowing one to observe the learning process at each level of abstraction. On all levels of the system, the representation of the data can be interpreted in both a symbolic and a sub-symbolic manner. This enables the architecture to learn efficiently using sub-symbolic methods and to employ symbolic inference.