Multi-Agent Reinforcement Learning Model based on Fuzzy Inference

퍼지 추론 기반의 멀티에이전트 강화학습 모델

  • 이봉근 (충북대학교 전기전자 컴퓨터공학부) ;
  • 정재두 (국방부 전자계산소) ;
  • 류근호 (충북대학교 전기전자 컴퓨터공학부)
  • Published : 2009.10.28


Reinforcement learning is a sub area of machine learning concerned with how an agent ought to take actions in an environment so as to maximize some notion of long-term reward. In the case of multi-agent, especially, which state space and action space gets very enormous in compared to single agent, so it needs to take most effective measure available select the action strategy for effective reinforcement learning. This paper proposes a multi-agent reinforcement learning model based on fuzzy inference system in order to improve learning collect speed and select an effective action in multi-agent. This paper verifies an effective action select strategy through evaluation tests based on Robocup Keepaway which is one of useful test-beds for multi-agent. Our proposed model can apply to evaluate efficiency of the various intelligent multi-agents and also can apply to strategy and tactics of robot soccer system.


Multi-Agent;Reinforcement Learning


  1. E. Matthew, Taylor and Peter Stone., "Representation Transfer for Reinforcement Learning," AAAI 2007 Fall Symposium, Arlington, Virginia, 2007.
  2. E. Yang, and Gu., "Multi-Agent Reinforcement Learning for Multi-Robot System: A Survey," University of Essex Technical Report CSM-404, 2004.
  3. Marvin Minsky, Push Singh, and Aaron Sloman , The St. Thomas Common Sense Symposium: Designing Architectures for Human-Level Intelligence, AI Magazine, 25-2: Summer 2004, pp.113-124. 2004.
  4. Aaron Sloman and Ron Chrisley, Virtual Machines and Consciousness, Journal of Consciousness Studies 10, 4-5. 2003.
  5. 권기덕, 김인철, "적대적 멀티 에이전트 환경에서 효율적인 강화 학습을 위한 정책 모델링", 한국정보과학회 논문지: 소프트웨어 및 응용 제35권, 제3호, pp179-188, 2008.
  6. R. S. Sutton and A. G. Barto, "Reinforcement Learning: An Introduction," MIT Press, 1998.
  7. G. Tesauro, "Multi Agent Learning:Mini Tutorial," IBM Watson Research Center, 2000.
  8. C. J. C. H. Watkins and P. Dayan, "Technical notes: Q-Iearning," Maching Learning, Vol.8, pp.279-292, 1992.
  9. R. Fagin, "Combining Fuzzy Information from Multiple Systems," J. of Computer and System Sciences, Vol.58, pp.83-99. 1999.
  10. 이영아, 정경숙, 정태충, "퍼지 클러스터링을 이용한 강화학습의 함수근사", 한국정보처리학회논문지, 제10-B권, 제6호, pp.587-592, 2003
  11. Lionel Jouffe, "Fuzzy Infernce System Learning by Reinforcement Methods," IEEE Transactions on Systems, Man and Cybernetics pp.338-355, 1998.
  12. David McAllester and Peter Stone. Keeping the ball from CMUnited-99, Robocup-2000:Robocup IV, Springer Verlag, Berlin, 2001.
  13. Alexander A. Sherstov and Peter Stone, Function Approximation via Tile Coding: Automating Parameter Choice, In Proc. Symposium on Abstraction, Reinforcement, and Approximation(SARA -05), 2005.