Multagent Control Strategy Using Reinforcement Learning


The KIPS Transactions:PartB , Vol. 10, No. 3, pp. 249-256, Jun. 2003
10.3745/KIPSTB.2003.10.3.249,   PDF Download:

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.


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]
H. I. Lee and B. C. Kim, "Multagent Control Strategy Using Reinforcement Learning," The KIPS Transactions:PartB , vol. 10, no. 3, pp. 249-256, 2003. DOI: 10.3745/KIPSTB.2003.10.3.249.

[ACM Style]
Hyong Ill Lee and Byung Cheon Kim. 2003. Multagent Control Strategy Using Reinforcement Learning. The KIPS Transactions:PartB , 10, 3, (2003), 249-256. DOI: 10.3745/KIPSTB.2003.10.3.249.