Intrinsic motivations and open-ended learning

TL;DR

This paper reviews the concept of intrinsic motivations across psychology, neuroscience, and machine learning, proposing a taxonomy and linking biological insights to computational models for open-ended learning.

Contribution

It provides a comprehensive taxonomy of intrinsic motivations and connects biological mechanisms to computational models in robotics and machine learning.

Findings

Biological mechanisms underpin intrinsic motivations in animals and humans.

Computational models operationalize intrinsic motivations based on biological concepts.

Open challenges include integrating biological insights into scalable learning algorithms.

Abstract

There is a growing interest and literature on intrinsic motivations and open-ended learning in both cognitive robotics and machine learning on one side, and in psychology and neuroscience on the other. This paper aims to review some relevant contributions from the two literature threads and to draw links between them. To this purpose, the paper starts by defining intrinsic motivations and by presenting a computationally-driven theoretical taxonomy of their different types. Then it presents relevant contributions from the psychological and neuroscientific literature related to intrinsic motivations, interpreting them based on the grid, and elucidates the mechanisms and functions they play in animals and humans. Endowed with such concepts and their biological underpinnings, the paper next presents a selection of models from cognitive robotics and machine learning that computationally operationalise the concepts of intrinsic motivations and links them to biology concepts. The contribution finally presents some of the open challenges of the field from both the psychological/neuroscientific and computational perspectives.