Modeling agent self-awareness, individual performance and collaborative behavior

Chung Yuan Huang*, Sheng Wen Wang, Chuen-Tsai Sun

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


In the history of artificial intelligence (AI), primary agent focuses have been external environments, outside incentives, and behavioral responses. Internal operation mechanisms (i.e., attending to the self in the same manner as human self-awareness) have never been a concern for AI agent. Obviously, the learning concepts by which one pays attention to oneself has always been ignored by artificial intelligence researchers. However, we integrated a self-awareness mechanism into an agent's learning architecture, so that not only are an agent's thinking and behaviors closer to the ways that people operate, but also to allow agent-based social simulations to be even more akin to the real world. Our research objectives include: a) to propose a self-awareness agent model including external learning mechanism and internal cognitive capacity combining with having super-ego and ego personalities; b) apply an iterated Prisoner's Dilemma game to represent the conflicts caused by public good and private interest in an agents' society, and analyze the effects of an agent's self-awareness capacity upon its individual performance and social cooperation behavior. Our goal is to show the ability of a cognitive learning model to improve intelligent agent performance and support collaborative agent behavior. We believe additional simulations and analyses will indicate enriched social benefits, even in cases where only a few agents achieve limited self-awareness capabilities.

Original languageEnglish
Title of host publicationWCICA 2011 - 2011 World Congress on Intelligent Control and Automation, Conference Digest
Number of pages5
StatePublished - 9 Sep 2011
Event2011 World Congress on Intelligent Control and Automation, WCICA 2011 - Taipei, Taiwan
Duration: 21 Jun 201125 Jun 2011

Publication series

NameProceedings of the World Congress on Intelligent Control and Automation (WCICA)


Conference2011 World Congress on Intelligent Control and Automation, WCICA 2011


  • Iterated Prisoner's Dilemma
  • Self-awareness agents
  • Tit-for-Tat strategy
  • Win-stay and Lose-shift strategy

Fingerprint Dive into the research topics of 'Modeling agent self-awareness, individual performance and collaborative behavior'. Together they form a unique fingerprint.

Cite this