Thumbnail Image
Publication

Multi-Agent Reinforcement Learning for Swarm Retrieval with Evolving Neural Network

Vaughan, Neil
Advisors
Editors
Other Contributors
Affiliation
Royal Academy of Engineering; University of Chester
EPub Date
Publication Date
2018-07-07
Submitted Date
Collections
Computer Science
Show all metadata
Files
Thumbnail Image
Main chapter
Adobe PDF, 444.57 KB
Other Titles
Abstract
This research investigates methods for evolving swarm communica-tion in a sim-ulated colony of ants using pheromone when foriaging for food. This research implemented neuroevolution and obtained the capability to learn phero-mone communication autonomously. Building on previous literature on phero-mone communication, this research applies evolution to adjust the topology and weights of an artificial neural network (ANN) which controls the ant behaviour. Compar-ison of performance is made between a hard-coded benchmark algorithm (BM1), a fixed topology ANN and neuroevolution of the ANN topology and weights. The resulting neuroevolution produced a neural network which was suc-cessfully evolved to achieve the task objective, to collect food and return it to a location.
Citation
Vaughan, N. (2018) Multi-agent reinforcement learning for swarm retrieval with evolving neural network. In V. Vouloutsi, et al. (Eds.) Biomimetic and Biohybrid Systems 7th International Conference, Living Machines, Paris, France, July 17–20, 2018.
Publisher
Springer
Journal
Research Unit
URI
http://hdl.handle.net/10034/621474
DOI
10.1007/978-3-319-95972-6_56
PubMed ID
PubMed Central ID
Type
Conference Contribution
Language
en
Description
The final publication is available at Springer via https://doi.org/10.1007/978-3-319-95972-6_56
Series/Report no.
Lecture Notes in Computer Science, volume 10928
ISSN
EISSN
ISBN
9783319959719
ISMN
Gov't Doc
Test Link
Sponsors
Additional Links
https://link.springer.com/chapter/10.1007/978-3-319-95972-6_56