DocumentCode :
2508749
Title :
Self-Aware Intelligent Agents in the Prisoner´s Dilemma
Author :
Huang, Chung-Yuan ; Wang, Sheng-Wen ; Sun, Chuen-Tsai
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Chang Gung Univ., Taoyuan, Taiwan
fYear :
2011
fDate :
18-19 June 2011
Firstpage :
127
Lastpage :
131
Abstract :
Self-aware individuals are more likely to consider whether their actions are appropriate in terms of public self-consciousness, and to use that information to execute behaviors that match external standards and/or expectations. The learning concepts through which individuals monitor themselves have generally been overlooked by artificial intelligence researchers. Here we report on our attempt to integrate a self-awareness mechanism into an agent´s learning architecture. Specifically, we describe (a) our proposal for a self-aware agent model that includes an external learning mechanism and internal cognitive capacity with super-ego and ego characteristics; and (b) our application of a version of the iterated prisoner´s dilemma representing conflicts between the public good and private interests to analyze the effects of self-awareness on an agent´s individual performance and cooperative behavior. Our results indicate that self-aware agents that consider public self-consciousness utilize rational analysis in a manner that promotes cooperative behavior and supports faster societal movement toward stability. We found that a small number of self-aware agents are sufficient for improving social benefits and resolving problems associated with collective irrational behaviors.
Keywords :
learning (artificial intelligence); multi-agent systems; agent learning architecture; external learning mechanism; prisoner dilemma; private interests; public good; public self consciousness; self aware intelligent agents; self awareness mechanism; Adaptation models; Automata; Biological system modeling; Computational modeling; Learning systems; Psychology; Stability analysis; cellular automata; public self-consciousness; self-aware agents; small-world networks; tit-for-tat strategy;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Future Computer Sciences and Application (ICFCSA), 2011 International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4577-0317-1
Type :
conf
DOI :
10.1109/ICFCSA.2011.36
Filename :
5968042
Link To Document :
بازگشت