Assessing the performance of different behavior selection architectures in a large and complex virtual environment

W.C. Ho; O. Avila-Garcia; C.L. Nehaniv

doi:10.1109/CEC.2005.1554706

Assessing the performance of different behavior selection architectures in a large and complex virtual environment

W.C. Ho
, O. Avila-Garcia
, C.L. Nehaniv

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

45 Downloads (Pure)

Abstract

We compare the performance of autonomous agents with three different behavior selection architectures (Static-Threshold, Winner-Takes-All and Voting- Based) in terms of survival in a large and complex dynamic virtual environment. Experiment results indicate both advantages and disadvantages when applying each architecture in such environmental conditions, and also shows that the performance of Voting-Based architecture is significantly sensitive to the balance of rates at which various environmental resources can serve to satisfy an agent's physiological needs. Some problems with behavior selection architectures are identified and possible solutions are proposed.

Original language	English
Title of host publication	In: Proceedings of the IEEE Congress on Evolutionary Computation - Special Session: Complex Adaptive Systems 1
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	359-365
DOIs	https://doi.org/10.1109/CEC.2005.1554706
Publication status	Published - 2005

Access to Document

10.1109/CEC.2005.1554706

900832.pdf

Cite this

Ho, W. C., Avila-Garcia, O., & Nehaniv, C. L. (2005). Assessing the performance of different behavior selection architectures in a large and complex virtual environment. In In: Proceedings of the IEEE Congress on Evolutionary Computation - Special Session: Complex Adaptive Systems 1 (pp. 359-365). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/CEC.2005.1554706

@inproceedings{878a8efeb73b4218bd2a75f32f04f679,

title = "Assessing the performance of different behavior selection architectures in a large and complex virtual environment",

abstract = "We compare the performance of autonomous agents with three different behavior selection architectures (Static-Threshold, Winner-Takes-All and Voting- Based) in terms of survival in a large and complex dynamic virtual environment. Experiment results indicate both advantages and disadvantages when applying each architecture in such environmental conditions, and also shows that the performance of Voting-Based architecture is significantly sensitive to the balance of rates at which various environmental resources can serve to satisfy an agent's physiological needs. Some problems with behavior selection architectures are identified and possible solutions are proposed.",

author = "W.C. Ho and O. Avila-Garcia and C.L. Nehaniv",

note = "This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.---- Copyright IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. --Original article can be found at: http://ieeexplore.ieee.org/xpl/RecentCon.jsppunumber=10417 DOI : 10.1109/CEC.2005.1554706",

year = "2005",

doi = "10.1109/CEC.2005.1554706",

language = "English",

pages = "359--365",

booktitle = "In: Proceedings of the IEEE Congress on Evolutionary Computation - Special Session: Complex Adaptive Systems 1",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Ho, WC, Avila-Garcia, O & Nehaniv, CL 2005, Assessing the performance of different behavior selection architectures in a large and complex virtual environment. in In: Proceedings of the IEEE Congress on Evolutionary Computation - Special Session: Complex Adaptive Systems 1. Institute of Electrical and Electronics Engineers (IEEE), pp. 359-365. https://doi.org/10.1109/CEC.2005.1554706

Assessing the performance of different behavior selection architectures in a large and complex virtual environment. / Ho, W.C.; Avila-Garcia, O.; Nehaniv, C.L.
In: Proceedings of the IEEE Congress on Evolutionary Computation - Special Session: Complex Adaptive Systems 1. Institute of Electrical and Electronics Engineers (IEEE), 2005. p. 359-365.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Assessing the performance of different behavior selection architectures in a large and complex virtual environment

AU - Ho, W.C.

AU - Avila-Garcia, O.

AU - Nehaniv, C.L.

N1 - This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.---- Copyright IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. --Original article can be found at: http://ieeexplore.ieee.org/xpl/RecentCon.jsppunumber=10417 DOI : 10.1109/CEC.2005.1554706

PY - 2005

Y1 - 2005

N2 - We compare the performance of autonomous agents with three different behavior selection architectures (Static-Threshold, Winner-Takes-All and Voting- Based) in terms of survival in a large and complex dynamic virtual environment. Experiment results indicate both advantages and disadvantages when applying each architecture in such environmental conditions, and also shows that the performance of Voting-Based architecture is significantly sensitive to the balance of rates at which various environmental resources can serve to satisfy an agent's physiological needs. Some problems with behavior selection architectures are identified and possible solutions are proposed.

AB - We compare the performance of autonomous agents with three different behavior selection architectures (Static-Threshold, Winner-Takes-All and Voting- Based) in terms of survival in a large and complex dynamic virtual environment. Experiment results indicate both advantages and disadvantages when applying each architecture in such environmental conditions, and also shows that the performance of Voting-Based architecture is significantly sensitive to the balance of rates at which various environmental resources can serve to satisfy an agent's physiological needs. Some problems with behavior selection architectures are identified and possible solutions are proposed.

U2 - 10.1109/CEC.2005.1554706

DO - 10.1109/CEC.2005.1554706

M3 - Conference contribution

SP - 359

EP - 365

BT - In: Proceedings of the IEEE Congress on Evolutionary Computation - Special Session: Complex Adaptive Systems 1

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Ho WC, Avila-Garcia O, Nehaniv CL. Assessing the performance of different behavior selection architectures in a large and complex virtual environment. In In: Proceedings of the IEEE Congress on Evolutionary Computation - Special Session: Complex Adaptive Systems 1. Institute of Electrical and Electronics Engineers (IEEE). 2005. p. 359-365 doi: 10.1109/CEC.2005.1554706

Assessing the performance of different behavior selection architectures in a large and complex virtual environment

Abstract

Access to Document

Fingerprint

Cite this