DocumentCode
2862987
Title
An improved multiagent reinforcement learning algorithm
Author
Meng, Xiangping ; Babu, Robert ; Busoniu, Lucian ; Chen, Yu ; Tan, Wanyu
Author_Institution
Dept. of Electr. Eng., Changchun Inst. of Technol., China
fYear
2005
fDate
19-22 Sept. 2005
Firstpage
337
Lastpage
343
Abstract
An improved reinforcement learning algorithm is proposed in this paper. This algorithm is based on linear programming method for finding the best-response policy. A pursuit example is tested and the results show that this algorithm has some properties, such as easy computation, simple operation procedure and can guarantee a good learning convergence.
Keywords
learning (artificial intelligence); linear programming; multi-agent systems; stochastic games; best-response policy; linear programming method; multiagent reinforcement learning algorithm; Control systems; Convergence; Learning; Linear programming; Multiagent systems; Power engineering and energy; Power engineering computing; Pursuit algorithms; Stochastic processes; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Agent Technology, IEEE/WIC/ACM International Conference on
Print_ISBN
0-7695-2416-8
Type
conf
DOI
10.1109/IAT.2005.42
Filename
1565563
Link To Document