Performance, robustness and effort cost comparison of machine learning mechanisms in FlatLand

G. N. Yannakakis; J. Levine; J. J. Hallam; M. Papageorgiou

Performance, robustness and effort cost comparison of machine learning mechanisms in FlatLand

G. N. Yannakakis, J. Levine, J. J. Hallam, M. Papageorgiou

Computer And Information Sciences

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

Abstract

This paper presents the first stage of research into a multi-agent complex environment, called “FlatLand” aiming at emerging complex and adaptive obstacle-avoidance and targetachievement behaviors by use of a variety of learning mechanisms. The presentation includes a detailed description of the FlatLand simulated world, the learning mechanisms used as well as an efficient method for comparing the mechanisms’ performance, robustness and required computational effort.

Original language	English
Title of host publication	11th IEEE Mediterranean Conference on Control and Automation (MED'03)
Number of pages	6
Publication status	Published - 1 Jun 2003

Keywords

back-propagation
genetic algorithms
machine learning
multi-agent
simulated worlds

Access to Document

Paper PDF

Fingerprint Dive into the research topics of 'Performance, robustness and effort cost comparison of machine learning mechanisms in FlatLand'. Together they form a unique fingerprint.

Cite this

@inproceedings{fad204fcfa8c4d64b1fa7cad59ba9725,

title = "Performance, robustness and effort cost comparison of machine learning mechanisms in FlatLand",

abstract = "This paper presents the first stage of research into a multi-agent complex environment, called “FlatLand” aiming at emerging complex and adaptive obstacle-avoidance and targetachievement behaviors by use of a variety of learning mechanisms. The presentation includes a detailed description of the FlatLand simulated world, the learning mechanisms used as well as an efficient method for comparing the mechanisms{\textquoteright} performance, robustness and required computational effort.",

keywords = "back-propagation, genetic algorithms, machine learning, multi-agent, simulated worlds",

author = "Yannakakis, {G. N.} and J. Levine and {J. Hallam}, J. and M. Papageorgiou",

year = "2003",

month = jun,

day = "1",

language = "English",

booktitle = "11th IEEE Mediterranean Conference on Control and Automation (MED'03)",

}

TY - GEN

T1 - Performance, robustness and effort cost comparison of machine learning mechanisms in FlatLand

AU - Yannakakis, G. N.

AU - Levine, J.

AU - J. Hallam, J.

AU - Papageorgiou, M.

PY - 2003/6/1

Y1 - 2003/6/1

N2 - This paper presents the first stage of research into a multi-agent complex environment, called “FlatLand” aiming at emerging complex and adaptive obstacle-avoidance and targetachievement behaviors by use of a variety of learning mechanisms. The presentation includes a detailed description of the FlatLand simulated world, the learning mechanisms used as well as an efficient method for comparing the mechanisms’ performance, robustness and required computational effort.

AB - This paper presents the first stage of research into a multi-agent complex environment, called “FlatLand” aiming at emerging complex and adaptive obstacle-avoidance and targetachievement behaviors by use of a variety of learning mechanisms. The presentation includes a detailed description of the FlatLand simulated world, the learning mechanisms used as well as an efficient method for comparing the mechanisms’ performance, robustness and required computational effort.

KW - back-propagation

KW - genetic algorithms

KW - machine learning

KW - multi-agent

KW - simulated worlds

UR - http://www.cis.strath.ac.uk/cis/research/publications/papers/strath_cis_publication_2187.pdf

M3 - Conference contribution book

BT - 11th IEEE Mediterranean Conference on Control and Automation (MED'03)

ER -