Evolutionary design of specialization

A. E. Eiben; G. S. Nitschke; M. C. Schut

doi:10.1109/ALIFE.2007.367825

Evolutionary design of specialization

A. E. Eiben^*
, G. S. Nitschke
, M. C. Schut

^*Corresponding author for this work

Vrije Universiteit Amsterdam

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

In this research, a neuro-evolution method called Collective Neuro-Evolution (CONE), is introduced for the design of neural controllers (agents) operating in collective behavior task domains. The efficacy of the CONE method for facilitating emergent behavioral specialization for the benefit of increasing task performance is tested in a pursuit-evasion and collective gathering task. For a comparative study, a conventional neuro-evolution method was applied to the same tasks. In both tasks, the CONE method derived behavioral specialization in groups of agents resulting in higher task performances, where as the conventional neuro-evolution method was unable to derive specialization resulting in comparatively lower task performances. © 2007 IEEE.

Original language	English
Title of host publication	Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007
Pages	417-424
DOIs	https://doi.org/10.1109/ALIFE.2007.367825
Publication status	Published - 2007
Externally published	Yes
Event	1st IEEE Symposium on Artificial Life, IEEE-ALife'07 - , United States Duration: 1 Apr 2007 → 5 Apr 2007

Publication series

Name	Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007

Conference

Conference	1st IEEE Symposium on Artificial Life, IEEE-ALife'07
Country/Territory	United States
Period	01/04/2007 → 05/04/2007

Access to Document

10.1109/ALIFE.2007.367825

Cite this

@inproceedings{ddaa1ccdbb234d2caf8532ff276046df,

title = "Evolutionary design of specialization",

abstract = "In this research, a neuro-evolution method called Collective Neuro-Evolution (CONE), is introduced for the design of neural controllers (agents) operating in collective behavior task domains. The efficacy of the CONE method for facilitating emergent behavioral specialization for the benefit of increasing task performance is tested in a pursuit-evasion and collective gathering task. For a comparative study, a conventional neuro-evolution method was applied to the same tasks. In both tasks, the CONE method derived behavioral specialization in groups of agents resulting in higher task performances, where as the conventional neuro-evolution method was unable to derive specialization resulting in comparatively lower task performances. {\textcopyright} 2007 IEEE.",

author = "Eiben, \{A. E.\} and Nitschke, \{G. S.\} and Schut, \{M. C.\}",

year = "2007",

doi = "10.1109/ALIFE.2007.367825",

language = "English",

series = "Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007",

pages = "417--424",

booktitle = "Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007",

note = "1st IEEE Symposium on Artificial Life, IEEE-ALife'07 ; Conference date: 01-04-2007 Through 05-04-2007",

}

TY - GEN

T1 - Evolutionary design of specialization

AU - Eiben, A. E.

AU - Nitschke, G. S.

AU - Schut, M. C.

PY - 2007

Y1 - 2007

N2 - In this research, a neuro-evolution method called Collective Neuro-Evolution (CONE), is introduced for the design of neural controllers (agents) operating in collective behavior task domains. The efficacy of the CONE method for facilitating emergent behavioral specialization for the benefit of increasing task performance is tested in a pursuit-evasion and collective gathering task. For a comparative study, a conventional neuro-evolution method was applied to the same tasks. In both tasks, the CONE method derived behavioral specialization in groups of agents resulting in higher task performances, where as the conventional neuro-evolution method was unable to derive specialization resulting in comparatively lower task performances. © 2007 IEEE.

AB - In this research, a neuro-evolution method called Collective Neuro-Evolution (CONE), is introduced for the design of neural controllers (agents) operating in collective behavior task domains. The efficacy of the CONE method for facilitating emergent behavioral specialization for the benefit of increasing task performance is tested in a pursuit-evasion and collective gathering task. For a comparative study, a conventional neuro-evolution method was applied to the same tasks. In both tasks, the CONE method derived behavioral specialization in groups of agents resulting in higher task performances, where as the conventional neuro-evolution method was unable to derive specialization resulting in comparatively lower task performances. © 2007 IEEE.

UR - https://www.scopus.com/pages/publications/34548787716

U2 - 10.1109/ALIFE.2007.367825

DO - 10.1109/ALIFE.2007.367825

M3 - Conference contribution

T3 - Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007

SP - 417

EP - 424

BT - Proceedings of the 2007 IEEE Symposium on Artificial Life, CI-ALife 2007

T2 - 1st IEEE Symposium on Artificial Life, IEEE-ALife'07

Y2 - 1 April 2007 through 5 April 2007

ER -

Evolutionary design of specialization

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this