Observation, communication and intelligence in agent-based systems

Nader Chmait; David L. Dowe; David G. Green; Yuan-Fang Li

doi:10.1007/978-3-319-21365-1_6

Observation, communication and intelligence in agent-based systems

Nader Chmait, David L. Dowe, David G. Green, Yuan-Fang Li

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

9 Citations (Scopus)

Abstract

The intelligence of multiagent systems is known to depend
on the communication and observation abilities of its agents. However
it is not clear which factor has the greater influence. By following an information-theoretical approach, this study quantifies and analyzes the impact of these two factors on the intelligence of multiagent systems. Using machine intelligence tests, we evaluate and compare the performance of collaborative agents across different communication and observation abilities of measurable entropies. Results show that the effectiveness of multiagent systems with low observation/perception abilities can be significantly improved by using high communication entropies within the agents in the system. We also identify circumstances where these assumptions fail, and analyze the dependency between the studied factors.

Original language	English
Title of host publication	Artificial General Intelligence: 8th International Conference, AGI 2015
Editors	Jordi Bieger, Ben Goertzel, Alexey Potapov
Place of Publication	Cham Switzerland
Publisher	Springer
Pages	50-59
Number of pages	10
ISBN (Print)	9783319213644
DOIs	https://doi.org/10.1007/978-3-319-21365-1_6
Publication status	Published - 2015
Event	Conference on Artificial General Intelligence (AGI) 2015 - Berlin, Germany Duration: 22 Jul 2015 → 25 Jul 2015 Conference number: 8th http://agi-conf.org/2015/ https://link.springer.com/book/10.1007/978-3-319-21365-1 (Proceedings)

Conference

Conference	Conference on Artificial General Intelligence (AGI) 2015
Abbreviated title	AGI 2015
Country/Territory	Germany
City	Berlin
Period	22/07/15 → 25/07/15
Internet address	http://agi-conf.org/2015/ https://link.springer.com/book/10.1007/978-3-319-21365-1 (Proceedings)

Access to Document

10.1007/978-3-319-21365-1_6

Cite this

@inproceedings{f05576e0d8324183888f80220a9a6f63,

title = "Observation, communication and intelligence in agent-based systems",

abstract = "The intelligence of multiagent systems is known to dependon the communication and observation abilities of its agents. Howeverit is not clear which factor has the greater influence. By following an information-theoretical approach, this study quantifies and analyzes the impact of these two factors on the intelligence of multiagent systems. Using machine intelligence tests, we evaluate and compare the performance of collaborative agents across different communication and observation abilities of measurable entropies. Results show that the effectiveness of multiagent systems with low observation/perception abilities can be significantly improved by using high communication entropies within the agents in the system. We also identify circumstances where these assumptions fail, and analyze the dependency between the studied factors.",

author = "Nader Chmait and Dowe, {David L.} and Green, {David G.} and Yuan-Fang Li",

year = "2015",

doi = "10.1007/978-3-319-21365-1_6",

language = "English",

isbn = "9783319213644",

pages = "50--59",

editor = "Jordi Bieger and Ben Goertzel and Alexey Potapov",

booktitle = "Artificial General Intelligence: 8th International Conference, AGI 2015",

publisher = "Springer",

note = "Conference on Artificial General Intelligence (AGI) 2015, AGI 2015 ; Conference date: 22-07-2015 Through 25-07-2015",

url = "http://agi-conf.org/2015/, https://link.springer.com/book/10.1007/978-3-319-21365-1",

}

Chmait, N, Dowe, DL, Green, DG & Li, Y-F 2015, Observation, communication and intelligence in agent-based systems. in J Bieger, B Goertzel & A Potapov (eds), Artificial General Intelligence: 8th International Conference, AGI 2015. Springer, Cham Switzerland, pp. 50-59, Conference on Artificial General Intelligence (AGI) 2015, Berlin, Berlin, Germany, 22/07/15. https://doi.org/10.1007/978-3-319-21365-1_6

Observation, communication and intelligence in agent-based systems. / Chmait, Nader; Dowe, David L.; Green, David G. et al.
Artificial General Intelligence: 8th International Conference, AGI 2015. ed. / Jordi Bieger; Ben Goertzel; Alexey Potapov. Cham Switzerland: Springer, 2015. p. 50-59.

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

TY - GEN

T1 - Observation, communication and intelligence in agent-based systems

AU - Chmait, Nader

AU - Dowe, David L.

AU - Green, David G.

AU - Li, Yuan-Fang

N1 - Conference code: 8th

PY - 2015

Y1 - 2015

N2 - The intelligence of multiagent systems is known to dependon the communication and observation abilities of its agents. Howeverit is not clear which factor has the greater influence. By following an information-theoretical approach, this study quantifies and analyzes the impact of these two factors on the intelligence of multiagent systems. Using machine intelligence tests, we evaluate and compare the performance of collaborative agents across different communication and observation abilities of measurable entropies. Results show that the effectiveness of multiagent systems with low observation/perception abilities can be significantly improved by using high communication entropies within the agents in the system. We also identify circumstances where these assumptions fail, and analyze the dependency between the studied factors.

AB - The intelligence of multiagent systems is known to dependon the communication and observation abilities of its agents. Howeverit is not clear which factor has the greater influence. By following an information-theoretical approach, this study quantifies and analyzes the impact of these two factors on the intelligence of multiagent systems. Using machine intelligence tests, we evaluate and compare the performance of collaborative agents across different communication and observation abilities of measurable entropies. Results show that the effectiveness of multiagent systems with low observation/perception abilities can be significantly improved by using high communication entropies within the agents in the system. We also identify circumstances where these assumptions fail, and analyze the dependency between the studied factors.

U2 - 10.1007/978-3-319-21365-1_6

DO - 10.1007/978-3-319-21365-1_6

M3 - Conference Paper

SN - 9783319213644

SP - 50

EP - 59

BT - Artificial General Intelligence: 8th International Conference, AGI 2015

A2 - Bieger, Jordi

A2 - Goertzel, Ben

A2 - Potapov, Alexey

PB - Springer

CY - Cham Switzerland

T2 - Conference on Artificial General Intelligence (AGI) 2015

Y2 - 22 July 2015 through 25 July 2015

ER -