ToyArchitecture: Unsupervised learning of interpretable models of the environment

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 often uncomputable, or lack practical implementations. In this paper we attempt to follow a big picture view while also pro...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2020-05, Vol.15 (5), p.e0230432-e0230432
Main Authors: Vítků, Jaroslav, Dluhoš, Petr, Davidson, Joseph, Nikl, Matěj, Andersson, Simon, Paška, Přemysl, Šinkora, Jan, Hlubuček, Petr, Stránský, Martin, Hyben, Martin, Poliak, Martin, Feyereisl, Jan, Rosa, Marek
Format: Article
Language:English
Subjects:
Algorithms
Analysis
Architecture
Artificial Intelligence
Biology and Life Sciences
Cognition & reasoning
Compression
Computer and Information Sciences
Computer architecture
Data compression
Deep learning
Engineering and Technology
Environment
Environment models
Experiments
Hierarchical organization (Computers)
Humans
Intelligence
Learning
Learning - physiology
Machine learning
Methods
Neural Networks, Computer
Novels
Physical Sciences
Reinforcement, Psychology
Representations
Social Sciences
Symbolism
Unsupervised learning
Unsupervised Machine Learning
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 often uncomputable, or lack practical implementations. In this paper we attempt to follow a big picture view while also providing a particular theory and its implementation to present a novel, purposely simple, and interpretable hierarchical architecture. This architecture incorporates the unsupervised learning of a model of the environment, learning the influence of one's own actions, model-based reinforcement learning, hierarchical planning, and symbolic/sub-symbolic integration in general. The learned model is stored in the form of hierarchical representations which are increasingly more abstract, but can retain details when needed. We demonstrate the universality of the architecture by testing it on a series of diverse environments ranging from audio/visual compression to discrete and continuous action spaces, to learning disentangled representations.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0230432