Bat q-learning algorithm
Author
Source
Jordanian Journal of Computetrs and Information Technology
Issue
Vol. 3, Issue 1 (30 Apr. 2017), pp.51-70, 20 p.
Publisher
Princess Sumaya University for Technology
Publication Date
2017-04-30
Country of Publication
Jordan
No. of Pages
20
Main Subjects
Abstract EN
Cooperative Q-learning approach allows multiple learners to learn independently and then share their Q-values among each other using a Q-value sharing strategy.
A main problem with this approach is that the solutions of the learners may not converge to optimality, because the optimal Q-values may not be found.
Another problem is that some cooperative algorithms perform very well with single-task problems, but quite poorly with multi-task problems.
This paper proposes a new cooperative Q-learning algorithm called the Bat Q-learning algorithm (BQ-learning) that implements a Q-value sharing strategy based on the Bat algorithm.
The Bat algorithm is a powerful optimization algorithm that increases the possibility of finding the optimal Q-values by balancing between the exploration and exploitation of actions by tuning the parameters of the algorithm.
The BQ-learning algorithm was tested using two problems: the shortest path problem (single-task problem) and the taxi problem (multi-task problem).
The experimental results suggest that BQ-learning performs better than single-agent Q-learning and some well-known cooperative Q-learning algorithms.
American Psychological Association (APA)
Abd al-Ghani, Bilal H.. 2017. Bat q-learning algorithm. Jordanian Journal of Computetrs and Information Technology،Vol. 3, no. 1, pp.51-70.
https://search.emarefa.net/detail/BIM-1415923
Modern Language Association (MLA)
Abd al-Ghani, Bilal H.. Bat q-learning algorithm. Jordanian Journal of Computetrs and Information Technology Vol. 3, no. 1 (Apr. 2017), pp.51-70.
https://search.emarefa.net/detail/BIM-1415923
American Medical Association (AMA)
Abd al-Ghani, Bilal H.. Bat q-learning algorithm. Jordanian Journal of Computetrs and Information Technology. 2017. Vol. 3, no. 1, pp.51-70.
https://search.emarefa.net/detail/BIM-1415923
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 68-70
Record ID
BIM-1415923