Specialization Versus Re-Specialization: Effects Of Hebbian Learning In A Dynamic Environment
Abstract
Specializing on a subset of tasks available within a system allows agents to more efficiently fulfill system demands. When demands change, agents need to Re-Specialize. Since Re-Specialization inherently requires undoing some prior Specialization, the opposing effort often results in agents set-ding on a worse task allocation than after Specialization, even when presented with similar demands. In this work, we demonstrate these task allocation differences by looking at how well demands are fulfilled, as well as how much task switching is happening within the system. We analyze what causes the observed differences and discuss potential approaches to improving Re-Specialization in the future.
Publication Date
1-1-2018
Publication Title
Proceedings of the 31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018
Number of Pages
354-359
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
85071955790 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85071955790
STARS Citation
Kazakova, Vera A. and Wu, Annie S., "Specialization Versus Re-Specialization: Effects Of Hebbian Learning In A Dynamic Environment" (2018). Scopus Export 2015-2019. 10050.
https://stars.library.ucf.edu/scopus2015/10050