Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

7-2015

Abstract

This paper analyzes advanced reinforcement learning techniques and compares some of them to motivated learning. Motivated learning is briefly discussed indicating its relation to reinforcement learning. A black box scenario for comparative analysis of learning efficiency in autonomous agents is developed and described. This is used to analyze selected algorithms. Reported results demonstrate that in the selected category of problems, motivated learning outperformed all reinforcement learning algorithms we compared with.

Keywords

motivated learning, reinforcement learning, goal creation, pain signals, desired resources

Discipline

Databases and Information Systems | Theory and Algorithms

Research Areas

Data Science and Engineering

Publication

Proceedings of 2015 International Joint Conference on Neural Networks, Killarney, Ireland, July 12-17

Volume

2015

First Page

1

Last Page

8

Identifier

10.1109/IJCNN.2015.7280723

Publisher

IEEE

City or Country

New York

Additional URL

https://doi.org/10.1109/IJCNN.2015.7280723

Share

COinS