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 proceedingConference PaperResearchpeer-review

    7 Citations (Scopus)


    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 languageEnglish
    Title of host publicationArtificial General Intelligence: 8th International Conference, AGI 2015
    EditorsJordi Bieger, Ben Goertzel, Alexey Potapov
    Place of PublicationCham Switzerland
    Number of pages10
    ISBN (Print)9783319213644
    Publication statusPublished - 2015
    EventConference on Artificial General Intelligence (AGI) 2015 - Berlin, Germany
    Duration: 22 Jul 201525 Jul 2015
    Conference number: 8th
    https://link.springer.com/book/10.1007/978-3-319-21365-1 (Proceedings)


    ConferenceConference on Artificial General Intelligence (AGI) 2015
    Abbreviated titleAGI 2015
    Internet address

    Cite this