Structured Memetic Automation for Online Human-like Social Behavior Learning

Yifeng Zeng, Xufeng Chen, Yew Soon Ong, Jing Tang, Yanping Xiang

Research output: Contribution to journalConference articleResearchpeer-review

30 Downloads (Pure)

Abstract

Meme automaton is an adaptive entity that autonomously acquires increasing level of capability and intelligence through embedded memes evolving independently or via social interactions. This paper embarks a study on memetic multiagent system (MeMAS) towards human-like social agents with memetic automaton. We introduce a potentially rich meme-inspired design and operational model, with Darwin’s theory of natural selection and Dawkins’ notion of a meme as the principal driving forces behind interactions among agents, whereby memes form the fundamental building blocks of the agents’ mind universe. To improve the efficiency and scalability of MeMAS, we propose memetic agents with structured memes in the present paper. Particularly, we focus on meme selection design where the commonly used elitist strategy is further improved by assimilating the notion of like-attracts-like in the human learning. We conduct experimental study on multiple problem domains and show performance of the proposed MeMAS on human-like social behavior.
Original languageEnglish
Pages (from-to)-
JournalIEEE Transactions on Evolutionary Computation
DOIs
Publication statusPublished - 1 Feb 2017

Fingerprint

Social Behavior
Automation
Multi agent systems
Multi-agent Systems
Automata
Natural Selection
Social Interaction
Driving Force
Building Blocks
Scalability
Experimental Study
Learning
Human
Interaction
Design

Cite this

@article{7f9778d41dad4187a0f166214402ff85,
title = "Structured Memetic Automation for Online Human-like Social Behavior Learning",
abstract = "Meme automaton is an adaptive entity that autonomously acquires increasing level of capability and intelligence through embedded memes evolving independently or via social interactions. This paper embarks a study on memetic multiagent system (MeMAS) towards human-like social agents with memetic automaton. We introduce a potentially rich meme-inspired design and operational model, with Darwin’s theory of natural selection and Dawkins’ notion of a meme as the principal driving forces behind interactions among agents, whereby memes form the fundamental building blocks of the agents’ mind universe. To improve the efficiency and scalability of MeMAS, we propose memetic agents with structured memes in the present paper. Particularly, we focus on meme selection design where the commonly used elitist strategy is further improved by assimilating the notion of like-attracts-like in the human learning. We conduct experimental study on multiple problem domains and show performance of the proposed MeMAS on human-like social behavior.",
author = "Yifeng Zeng and Xufeng Chen and Ong, {Yew Soon} and Jing Tang and Yanping Xiang",
year = "2017",
month = "2",
day = "1",
doi = "10.1109/TEVC.2016.2577593",
language = "English",
pages = "--",
journal = "IEEE Transactions on Evolutionary Computation",
issn = "1941-0026",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Structured Memetic Automation for Online Human-like Social Behavior Learning. / Zeng, Yifeng; Chen, Xufeng; Ong, Yew Soon; Tang, Jing; Xiang, Yanping.

In: IEEE Transactions on Evolutionary Computation, 01.02.2017, p. -.

Research output: Contribution to journalConference articleResearchpeer-review

TY - JOUR

T1 - Structured Memetic Automation for Online Human-like Social Behavior Learning

AU - Zeng, Yifeng

AU - Chen, Xufeng

AU - Ong, Yew Soon

AU - Tang, Jing

AU - Xiang, Yanping

PY - 2017/2/1

Y1 - 2017/2/1

N2 - Meme automaton is an adaptive entity that autonomously acquires increasing level of capability and intelligence through embedded memes evolving independently or via social interactions. This paper embarks a study on memetic multiagent system (MeMAS) towards human-like social agents with memetic automaton. We introduce a potentially rich meme-inspired design and operational model, with Darwin’s theory of natural selection and Dawkins’ notion of a meme as the principal driving forces behind interactions among agents, whereby memes form the fundamental building blocks of the agents’ mind universe. To improve the efficiency and scalability of MeMAS, we propose memetic agents with structured memes in the present paper. Particularly, we focus on meme selection design where the commonly used elitist strategy is further improved by assimilating the notion of like-attracts-like in the human learning. We conduct experimental study on multiple problem domains and show performance of the proposed MeMAS on human-like social behavior.

AB - Meme automaton is an adaptive entity that autonomously acquires increasing level of capability and intelligence through embedded memes evolving independently or via social interactions. This paper embarks a study on memetic multiagent system (MeMAS) towards human-like social agents with memetic automaton. We introduce a potentially rich meme-inspired design and operational model, with Darwin’s theory of natural selection and Dawkins’ notion of a meme as the principal driving forces behind interactions among agents, whereby memes form the fundamental building blocks of the agents’ mind universe. To improve the efficiency and scalability of MeMAS, we propose memetic agents with structured memes in the present paper. Particularly, we focus on meme selection design where the commonly used elitist strategy is further improved by assimilating the notion of like-attracts-like in the human learning. We conduct experimental study on multiple problem domains and show performance of the proposed MeMAS on human-like social behavior.

U2 - 10.1109/TEVC.2016.2577593

DO - 10.1109/TEVC.2016.2577593

M3 - Conference article

SP - -

JO - IEEE Transactions on Evolutionary Computation

JF - IEEE Transactions on Evolutionary Computation

SN - 1941-0026

ER -