Evolving team behaviors with specialization

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

doi:10.1007/s10710-012-9166-5

Evolving team behaviors with specialization

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

^*Corresponding author for this work

The University of Tokyo
Vrije Universiteit Amsterdam

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

This article evaluates Collective Neuro-Evolution (CONE), a cooperative co-evolutionary method for solving collective behavior tasks and increasing task performance via facilitating behavioral specialization in agent teams. Specialization is used as a problem solving mechanism, and its emergence is guided and regulated by CONE. CONE is comparatively evaluated with related methods in a simulated evolutionary robotics pursuit-evasion task. This task required multiple pursuer robots to cooperatively capture evader robots. Results indicate that CONE is appropriate for evolving specialized behaviors. The interaction of specialized behaviors produces behavioral heterogeneity in teams and collective prey capture behaviors that yield significantly higher performances compared to related methods. © Springer Science+Business Media, LLC 2012.

Original language	English
Pages (from-to)	493-536
Journal	Genetic Programming and Evolvable Machines
Volume	13
Issue number	4
DOIs	https://doi.org/10.1007/s10710-012-9166-5
Publication status	Published - Dec 2012
Externally published	Yes

Access to Document

10.1007/s10710-012-9166-5

Cite this

@article{4dda19dba8384e3a91f9da4169918f2d,

title = "Evolving team behaviors with specialization",

abstract = "This article evaluates Collective Neuro-Evolution (CONE), a cooperative co-evolutionary method for solving collective behavior tasks and increasing task performance via facilitating behavioral specialization in agent teams. Specialization is used as a problem solving mechanism, and its emergence is guided and regulated by CONE. CONE is comparatively evaluated with related methods in a simulated evolutionary robotics pursuit-evasion task. This task required multiple pursuer robots to cooperatively capture evader robots. Results indicate that CONE is appropriate for evolving specialized behaviors. The interaction of specialized behaviors produces behavioral heterogeneity in teams and collective prey capture behaviors that yield significantly higher performances compared to related methods. {\textcopyright} Springer Science+Business Media, LLC 2012.",

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

year = "2012",

month = dec,

doi = "10.1007/s10710-012-9166-5",

language = "English",

volume = "13",

pages = "493--536",

journal = "Genetic Programming and Evolvable Machines",

issn = "1389-2576",

publisher = "Springer New York",

number = "4",

}

TY - JOUR

T1 - Evolving team behaviors with specialization

AU - Nitschke, G. S.

AU - Eiben, A. E.

AU - Schut, M. C.

PY - 2012/12

Y1 - 2012/12

N2 - This article evaluates Collective Neuro-Evolution (CONE), a cooperative co-evolutionary method for solving collective behavior tasks and increasing task performance via facilitating behavioral specialization in agent teams. Specialization is used as a problem solving mechanism, and its emergence is guided and regulated by CONE. CONE is comparatively evaluated with related methods in a simulated evolutionary robotics pursuit-evasion task. This task required multiple pursuer robots to cooperatively capture evader robots. Results indicate that CONE is appropriate for evolving specialized behaviors. The interaction of specialized behaviors produces behavioral heterogeneity in teams and collective prey capture behaviors that yield significantly higher performances compared to related methods. © Springer Science+Business Media, LLC 2012.

AB - This article evaluates Collective Neuro-Evolution (CONE), a cooperative co-evolutionary method for solving collective behavior tasks and increasing task performance via facilitating behavioral specialization in agent teams. Specialization is used as a problem solving mechanism, and its emergence is guided and regulated by CONE. CONE is comparatively evaluated with related methods in a simulated evolutionary robotics pursuit-evasion task. This task required multiple pursuer robots to cooperatively capture evader robots. Results indicate that CONE is appropriate for evolving specialized behaviors. The interaction of specialized behaviors produces behavioral heterogeneity in teams and collective prey capture behaviors that yield significantly higher performances compared to related methods. © Springer Science+Business Media, LLC 2012.

UR - https://www.scopus.com/pages/publications/84867191936

U2 - 10.1007/s10710-012-9166-5

DO - 10.1007/s10710-012-9166-5

M3 - Article

SN - 1389-2576

VL - 13

SP - 493

EP - 536

JO - Genetic Programming and Evolvable Machines

JF - Genetic Programming and Evolvable Machines

IS - 4

ER -

Evolving team behaviors with specialization

Abstract

Access to Document

Other files and links

Fingerprint

Cite this