The Automatic Coordination Model for Multi - Agent System Using Learning Method


The KIPS Transactions:PartB , Vol. 8, No. 6, pp. 587-594, Dec. 2001
10.3745/KIPSTB.2001.8.6.587,   PDF Download:

Abstract

Multi-agent system fits to the distributed and open internet environments. In a multi-agent system, agents must cooperate with each other through a coordination procedure, when the conflicts between agents arise. Where those are caused by the point that each action acts for a purpose separately without coordination. But previous researches for coordination methods in multi-agent system have a deficiency that they cannot solve correctly the cooperation problem between agents, which have different goals in dynamic environment. In this paper, we suggest the automatic coordination model for multi-agent system using neural network and reinforcement learning in dynamic environment. We have competitive experiment between multi-agents that have complexity environment and diverse activity. And we analysis and evaluate effect of activity of multi-agents. The results show that the proposed method is proper.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
M. R. Lee and S. G. Kim, "The Automatic Coordination Model for Multi - Agent System Using Learning Method," The KIPS Transactions:PartB , vol. 8, no. 6, pp. 587-594, 2001. DOI: 10.3745/KIPSTB.2001.8.6.587.

[ACM Style]
Mal Rey Lee and Sang Geun Kim. 2001. The Automatic Coordination Model for Multi - Agent System Using Learning Method. The KIPS Transactions:PartB , 8, 6, (2001), 587-594. DOI: 10.3745/KIPSTB.2001.8.6.587.