Efficiency of goal-oriented communicating agents in different graph topologies

A study with Internet crawlers

A. Lőrincz, Katalin A. Lázár, Zsolt Palotai

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

To what extent does the communication make a goal-oriented community efficient in different topologies? In order to gain insight into this problem, we study the influence of learning method as well as that of the topology of the environment on the communication efficiency of crawlers in quest of novel information in different topics on the Internet. Individual crawlers employ selective learning, function approximation-based reinforcement learning (RL), and their combination. Selective learning, in effect, modifies the starting URL lists of the crawlers, whilst RL alters the URL orderings. Real data have been collected from the web and scale-free worlds, scale-free small world (SFSW), and random world environments (RWEs) have been created by link reorganization. In our previous experiments [ Zs. Palotai, Cs. Farkas, A. Lo{combining double acute accent}rincz, Is selection optimal in scale-free small worlds?, ComPlexUs 3 (2006) 158-168], the crawlers searched for novel, genuine documents and direct communication was not possible. Herein, our finding is reproduced: selective learning performs the best and RL the worst in SFSW, whereas the combined, i.e., selective learning coupled with RL is the best-by a slight margin-in scale-free worlds. This effect is demonstrated to be more pronounced when the crawlers search for different topic-specific documents: the relative performance of the combined learning algorithm improves in all worlds, i.e., in SFSW, in SFW, and in RWE. If the tasks are more complex and the work sharing is enforced by the environment then the combined learning algorithm becomes at least equal, even superior to both the selective and the RL algorithms in most cases, irrespective of the efficiency of communication. Furthermore, communication improves the performance by a large margin and adaptive communication is advantageous in the majority of the cases.

Original languageEnglish
Pages (from-to)127-134
Number of pages8
JournalPhysica A: Statistical Mechanics and its Applications
Volume378
Issue number1
DOIs
Publication statusPublished - May 1 2007

Fingerprint

communicating
learning
Reinforcement Learning
topology
Small World
Topology
Graph in graph theory
Learning Algorithm
reinforcement
communication
Margin
Function Approximation
Acute
Communication
margins
Sharing
Learning
lists
Experiment

Keywords

  • Communicating agents
  • Internet
  • Scale-free world
  • Small world

ASJC Scopus subject areas

  • Mathematical Physics
  • Statistical and Nonlinear Physics

Cite this

Efficiency of goal-oriented communicating agents in different graph topologies : A study with Internet crawlers. / Lőrincz, A.; Lázár, Katalin A.; Palotai, Zsolt.

In: Physica A: Statistical Mechanics and its Applications, Vol. 378, No. 1, 01.05.2007, p. 127-134.

Research output: Contribution to journalArticle

@article{15ec5308934b410eb6fb23e57d8a5e14,
title = "Efficiency of goal-oriented communicating agents in different graph topologies: A study with Internet crawlers",
abstract = "To what extent does the communication make a goal-oriented community efficient in different topologies? In order to gain insight into this problem, we study the influence of learning method as well as that of the topology of the environment on the communication efficiency of crawlers in quest of novel information in different topics on the Internet. Individual crawlers employ selective learning, function approximation-based reinforcement learning (RL), and their combination. Selective learning, in effect, modifies the starting URL lists of the crawlers, whilst RL alters the URL orderings. Real data have been collected from the web and scale-free worlds, scale-free small world (SFSW), and random world environments (RWEs) have been created by link reorganization. In our previous experiments [ Zs. Palotai, Cs. Farkas, A. Lo{combining double acute accent}rincz, Is selection optimal in scale-free small worlds?, ComPlexUs 3 (2006) 158-168], the crawlers searched for novel, genuine documents and direct communication was not possible. Herein, our finding is reproduced: selective learning performs the best and RL the worst in SFSW, whereas the combined, i.e., selective learning coupled with RL is the best-by a slight margin-in scale-free worlds. This effect is demonstrated to be more pronounced when the crawlers search for different topic-specific documents: the relative performance of the combined learning algorithm improves in all worlds, i.e., in SFSW, in SFW, and in RWE. If the tasks are more complex and the work sharing is enforced by the environment then the combined learning algorithm becomes at least equal, even superior to both the selective and the RL algorithms in most cases, irrespective of the efficiency of communication. Furthermore, communication improves the performance by a large margin and adaptive communication is advantageous in the majority of the cases.",
keywords = "Communicating agents, Internet, Scale-free world, Small world",
author = "A. Lőrincz and L{\'a}z{\'a}r, {Katalin A.} and Zsolt Palotai",
year = "2007",
month = "5",
day = "1",
doi = "10.1016/j.physa.2006.11.052",
language = "English",
volume = "378",
pages = "127--134",
journal = "Physica A: Statistical Mechanics and its Applications",
issn = "0378-4371",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Efficiency of goal-oriented communicating agents in different graph topologies

T2 - A study with Internet crawlers

AU - Lőrincz, A.

AU - Lázár, Katalin A.

AU - Palotai, Zsolt

PY - 2007/5/1

Y1 - 2007/5/1

N2 - To what extent does the communication make a goal-oriented community efficient in different topologies? In order to gain insight into this problem, we study the influence of learning method as well as that of the topology of the environment on the communication efficiency of crawlers in quest of novel information in different topics on the Internet. Individual crawlers employ selective learning, function approximation-based reinforcement learning (RL), and their combination. Selective learning, in effect, modifies the starting URL lists of the crawlers, whilst RL alters the URL orderings. Real data have been collected from the web and scale-free worlds, scale-free small world (SFSW), and random world environments (RWEs) have been created by link reorganization. In our previous experiments [ Zs. Palotai, Cs. Farkas, A. Lo{combining double acute accent}rincz, Is selection optimal in scale-free small worlds?, ComPlexUs 3 (2006) 158-168], the crawlers searched for novel, genuine documents and direct communication was not possible. Herein, our finding is reproduced: selective learning performs the best and RL the worst in SFSW, whereas the combined, i.e., selective learning coupled with RL is the best-by a slight margin-in scale-free worlds. This effect is demonstrated to be more pronounced when the crawlers search for different topic-specific documents: the relative performance of the combined learning algorithm improves in all worlds, i.e., in SFSW, in SFW, and in RWE. If the tasks are more complex and the work sharing is enforced by the environment then the combined learning algorithm becomes at least equal, even superior to both the selective and the RL algorithms in most cases, irrespective of the efficiency of communication. Furthermore, communication improves the performance by a large margin and adaptive communication is advantageous in the majority of the cases.

AB - To what extent does the communication make a goal-oriented community efficient in different topologies? In order to gain insight into this problem, we study the influence of learning method as well as that of the topology of the environment on the communication efficiency of crawlers in quest of novel information in different topics on the Internet. Individual crawlers employ selective learning, function approximation-based reinforcement learning (RL), and their combination. Selective learning, in effect, modifies the starting URL lists of the crawlers, whilst RL alters the URL orderings. Real data have been collected from the web and scale-free worlds, scale-free small world (SFSW), and random world environments (RWEs) have been created by link reorganization. In our previous experiments [ Zs. Palotai, Cs. Farkas, A. Lo{combining double acute accent}rincz, Is selection optimal in scale-free small worlds?, ComPlexUs 3 (2006) 158-168], the crawlers searched for novel, genuine documents and direct communication was not possible. Herein, our finding is reproduced: selective learning performs the best and RL the worst in SFSW, whereas the combined, i.e., selective learning coupled with RL is the best-by a slight margin-in scale-free worlds. This effect is demonstrated to be more pronounced when the crawlers search for different topic-specific documents: the relative performance of the combined learning algorithm improves in all worlds, i.e., in SFSW, in SFW, and in RWE. If the tasks are more complex and the work sharing is enforced by the environment then the combined learning algorithm becomes at least equal, even superior to both the selective and the RL algorithms in most cases, irrespective of the efficiency of communication. Furthermore, communication improves the performance by a large margin and adaptive communication is advantageous in the majority of the cases.

KW - Communicating agents

KW - Internet

KW - Scale-free world

KW - Small world

UR - http://www.scopus.com/inward/record.url?scp=33847021212&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847021212&partnerID=8YFLogxK

U2 - 10.1016/j.physa.2006.11.052

DO - 10.1016/j.physa.2006.11.052

M3 - Article

VL - 378

SP - 127

EP - 134

JO - Physica A: Statistical Mechanics and its Applications

JF - Physica A: Statistical Mechanics and its Applications

SN - 0378-4371

IS - 1

ER -