The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Multagent Control Strategy Using Reinforcement Learning

강화학습을 이용한 다중 에이전트 제어 전략

  • 이형일 (김포대학 소프트웨어제작과) ;
  • 김병천 (한경대학교 웹정보공학과)
  • Published : 2003.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

The most important problems in the multi-agent system are to accomplish a goal through the efficient coordination of several agents and to prevent collision with other agents. In this paper, we propose a new control strategy for succeeding the goal of the prey pursuit problem efficiently. Our control method uses reinforcement learning to control the multi-agent system and consider the distance as well as the space relationship between the agents in the state space of the prey pursuit problem.

다중 에이전트 시스템에서 가장 중요한 문제는 여러 에이전트가 서로 효율적인 협동(coordination)을 통해서 목표(goal)를 성취하는 것과 다른 에이전트들과의 충돌(collision) 을 방지하는 것이다. 본 논문에서는 먹이 추적 문제의 목표를 효율적으로 성취하기 위해 새로운 전략 방법을 제안한다. 제안된 제어 전략은 다중 에이전트를 제어하기 위해 강화 학습을 이용하였고, 에이전트들간의 거리관계와 공간 관계를 고려하였다.

Keywords

References

  1. M. L. Minsky, Theory of Neural-Analoy Reinforcement Systems and Application to th Brain-Model Problem, Ph.D.Thesis, Princeton University, Princeton, 1954
  2. M. L. Minsky, 'Step towards aritificial intelligence,' In Proceedings of the Institute of Radio Engineers, 49, pp.8-30, 1961
  3. A. G. Barto, D. A. White and D. A. Sofge, 'Reinforcement Learning and adaptive critic methods,' Handbook of Intelligent Control, pp.469-491, 1992
  4. A. W. Moore and C. G. Atkeson, 'Prioritized sweeping: Reinforcement Learning with less data and less real time,' Machine Leraning, 13, pp.103-130, 1993
  5. C. W. Anderson, 'Learning to control an inverted pendulum using neural networks,' IEEE Control Systems Magazine, 9, pp.31-37 https://doi.org/10.1109/37.24809
  6. F. S. Ho, 'Traffic flow modeling and control using artificial neural networks,' IEEE Control Systems, 16(5), pp.16-26, 1996 https://doi.org/10.1109/37.537205
  7. R. H. Crites and A. G. Barto, 'Improving Elevator Performance Using Reinforcement Learning,' Advances in Neural Information Processing Systems, 8, MIT Press, Cambridge, MA, 1996
  8. S. P. Singh, 'Transfer of Leraning by Composing Solutions of Elemental Sequential Tasks,' Machine Leraning, 8, pp.323-339, 1992 https://doi.org/10.1007/BF00992700
  9. C. J. C. H. Watkins, 'Technical note : Q-leraning,' Machine Leraning, 8, pp.279-292
  10. R. S. Sutton, A. G. Barto, 'Reinforcement Learning : An Introduction,' MIT Press, 1988
  11. M. Benda, V. Jagannathan and R. Dodhiawala, 'On optimalcooperation of knowledge source-an empirical invarstigation,' Technical Report BCS-G2010-28, Boeing Advanced Technology Center, Boeing Computing Services, Seattle, Washington, July, 1986
  12. Peter Stone and Manuela Veloso, 'Multiagent System : A Survey from a Machine Learning,' Technical Report CMU-CS-97-193, The University of Carnegie Mellon, December, 1997
  13. Sandip Sen, Mahendra Sekaran and John Hale, 'Learning to coordinate without sharing information,' National Conference on Aritificial Intelligence, pp.426-431, July, 1994
  14. Tomas Haynes and Sandip Sen, 'Evloving behavioral strategies in predators and prey,' Adaptation and Learning in Multiagent System, Springer Verlag, Berlin, pp.113-126, 1996
  15. L. M. Stephens and M. B. Merx, 'The effect of agent control strategy on the performance of a DAI pursuit problem,' In Proceeding of the 1990 Distributed AI Workshop, October, 1990