DocumentCode :
3161167
Title :
Cooperative reinforcement learning based on zero-sum games
Author :
Hwang, Kao-Shing ; Chiou, Jeng-Yih ; Chen, Tse-Yu
Author_Institution :
Dept. of X of Electr. Eng., Nat. Chung Cheng Univ., Chiayi
fYear :
2008
fDate :
20-22 Aug. 2008
Firstpage :
2973
Lastpage :
2976
Abstract :
The objective of this paper is to develop a strategy system in a robot soccer system with cooperative ability which is improved by self-learning. A reinforcement learning method based on the zero-sum game theory is developed in this paper. It enforces learning systems to choose an appropriate strategy complying with the opponentpsilas actions. In order to achieve the purpose of cooperation, the system consists of two sub systems, one is a role assignment system, and the other is a reinforcement learning system.
Keywords :
game theory; mobile robots; unsupervised learning; cooperative reinforcement learning; robot soccer system; self-learning; zero-sum games; Control system synthesis; Costs; Electronic mail; Game theory; Learning systems; Multiagent systems; Robot kinematics; Testing; Q-learning; cooperation; reinforcement learning; robot soccer system; strategy system; zero-sum game theory;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
SICE Annual Conference, 2008
Conference_Location :
Tokyo
Print_ISBN :
978-4-907764-30-2
Electronic_ISBN :
978-4-907764-29-6
Type :
conf
DOI :
10.1109/SICE.2008.4655172
Filename :
4655172
Link To Document :
بازگشت