DOI QR코드

DOI QR Code

A Study to Generate a Theory of Coordination for Intelligent Agent Societies

지능형 에이전트 집단을 위한 조정 이론 생성에 관한 연구

  • 김은경 (한국기술교육대학교 정보기술공학부)
  • Published : 2002.04.01

Abstract

In bulding Intelligent Agent Societies (IAS), it is very important to design and implement coordination in accordance with the known requirement and anticipated working conditions. Coordination consists of a set of mechanisms necessary for the effective operation of IAS. Currently, there is little theoretical support that could help in this research is to generate an empirically-based solving systems in which all agent share an identical goal structure and fully cooperate. And we developed a simulation model called "P-System" which produces basic data to be used for statistical analysis to generate a theory of coordination. Coordination among agent in the P-System is dependent on 23 control variables calld TEs(tweakable emtities.)And the level of coordination is represennted by an independent variabe called QMC (Quality Measure Coordination) expressed in numerical terms according tn the definiion of this study. Also, we have studied how to select unbiased subset from the huge total experimental space of the P-System and how to decide the scale of the subset.

지능형 에이전트 집단(Intelligent Agent Societies (IAS)을 구축함에 있어서 예상되는 여러 작업 조건과 요구사항에 따라 조정을 설계, 구현하는 것은 매우 중요하며, 조정은 IAS의 효과적인 운영을 위해 필요한 여러 가지 메카니즘들로 구성된다. 하지만 현재 이러한 과정에 도움이 되는 이론적인 지원이 거의 없는 것이 현실이다. 본 연구에서는 효과적이고 실질적인 IAS를 설계하는데 도움이 되는, 실험에 근거한 조정 이론을 개발하는 것을 최종 목표로, 우선 모든 에이전트가 공통된 목표를 공유하면서 전적으로 협력하는 분산문제해결 시스템으로 범위를 설정하고, 조정 이론을 생성하기 위한 기초 분석자료를 제공해 줄 시뮬레이션 모델인 "P-System"을 개발하였다. P-System에서 에이전트출간의 조정은 TE(tweakable entity)라 칭한 23개의 제어 변수에 종속적이며, 조정의 수준은 본 연구의 정의에 따라 수치로 표현된 QMC (Quality Measure of Coordination)라 칭한 종속 변수로 표현된다. 특히 본 연구에서는 P-System의 엄청난 전체 실험공간으로부터 편중되지 않은 서브셋을 선택하는 방법과 적절한 서브셋의 규모를 결정하는 방안에 대해서 연구하였다.대해서 연구하였다.

Keywords

References

  1. Gasser, L., 'DAI approaches to coordination,' In Gasser, L., editors, Distributed Artificial Intelligence: Theory and Praxis, Kluwer, pp.31-51, 1992
  2. Jennings, N. R., 'Commitments and conventions : The foundation of coordination in multi-agent systems,' Knowledge Engineering Rev., 81323-250, 1993 https://doi.org/10.1017/S0269888900000205
  3. Decker, K. S., 'TfiMS : A framework for analysis and design of coordination mechanisms,' In O'Hare, G. & Jennflings, N., eds., Foundations of DAI, Wiley, 1995
  4. Jennings, N. R., 'Controlling cooperative problem solving in industrial multi-agent systems using joint intentions,' Artificial Intelligence, 75 : pp.195-240, 1993 https://doi.org/10.1016/0004-3702(94)00020-2
  5. Findler, N. V. and Elder, G. D., 'Multi-agent coordination and cooperation in a dynamic environment with limited resources,' Artificial Intelligence in Engineering, 9, pp.229-238, 1994 https://doi.org/10.1016/0954-1810(95)00011-7
  6. Findler, N. V. and Malyankar, R. M., 'A methodology for modeling coordination in intelligent agent societies,' Computational and Mathematical Organization Theory, 4, pp.317-345, 1998 https://doi.org/10.1023/A:1009634413228
  7. Peter, S. H., An Empirically-Based Theory of Coordination for Intelligent Agent Societies, Master dissertation, Dept. of Computer Science and Eng., Arizona State University, 1998
  8. Findler, N. V. and Malyankar, R. M., 'Social structures and the problem of coordination in intelligent agent societies,' Invited talk at the Special Session on Agent-Based Simulation, Planning and Control in IMACS World Congress, pp.122-132, 2000
  9. Findler, N. V. and Malyankar, R. M., 'An Empirical Approach to a Theory of Coordination Part I : Design Principles and First Results,' Computational and Mathematical Organization Theory, 6, pp.1l9-144, 2000 https://doi.org/10.1023/A:1009681418003
  10. Findler, N. V. and Malyankar, R. M., Heck, P. S., 'The effects of satisficing models on coordination,' AAAI Spring Symposium, pp.39-45, 1998
  11. Findler, N. V. and Lo, R., 'Empirical studies on distributed planning for air traffic control. Part II : Experimental results,' Journal of Transportation Engineering, 119, pp.681-692, 1993 https://doi.org/10.1061/(ASCE)0733-947X(1993)119:5(681)
  12. Cohen, P. R., Empirical Methods for Artificial Intelligence, The MIT Press, pp.1-103, 1995
  13. Axelrod, R., The Evolution of Cooperation, Basic Books, NY, 1984
  14. Nurusis, M. J., SPSS 10.0 Guide to Data Analysis, Pearson Pub., 2000
  15. D. G. Kleinbaum and L. L. Kupper, Applied Regression Analysis and Other Multivariable Methods, Duxbury Press, 1978