Behavioural Plasticity Can Help Evolving Agents in Dynamic Environments but at the Cost of Volatility

Abstract

Neural networks have been widely used in agent learning architectures; however, learnings for one task might nullify learnings for another. Behavioural plasticity enables humans and animals alike to respond to environmental changes without degrading learned knowledge; this can be achieved by regulating behaviour with neuromodulation—a biological process found in the brain. We demonstrate that by modulating activity-propagating signals, neurally trained agents evolving to solve tasks in dynamic environments that are prone to change can expect a significantly higher fitness than non-modulatory agents and also achieve their goals more often. Further, we show that while behavioural plasticity can help agents to achieve goals in these variable environments, this ability to overcome environmental changes with greater success comes at the cost of highly volatile evolution.

Publication DOI: https://doi.org/10.1145/3487918
Divisions: College of Engineering & Physical Sciences > School of Informatics and Digital Engineering > Computer Science
College of Engineering & Physical Sciences > Aston Institute of Urban Technology and the Environment (ASTUTE)
College of Engineering & Physical Sciences
Additional Information: © 2021 Copyright held by the owner/author(s)
Uncontrolled Keywords: Software,Computer Science (miscellaneous),Control and Systems Engineering
Publication ISSN: 1556-4703
Full Text Link:
Related URLs: https://dl.acm. ... 10.1145/3487918 (Publisher URL)
PURE Output Type: Article
Published Date: 2021-12-20
Accepted Date: 2021-09-01
Authors: Barnes, Chloe M.
Ekárt, Anikó (ORCID Profile 0000-0001-6967-5397)
Ellefsen, Kai Olav
Glette, Kyrre
Lewis, Peter R.
Tørresen, Jim

Download

[img]

Version: Published Version

| Preview

Export / Share Citation


Statistics

Additional statistics for this record