DocumentCode :
3180342
Title :
Research on cooperation and learning in multi-agent system
Author :
Zheng, Shuli ; Luo, Xiangfeng ; Luo, Zhenghu ; Yang, Jingan ; Jingan Yang
Author_Institution :
Inst. of Artificial Intelligence, Hefei Univ. of Technol., China
Volume :
2
fYear :
2002
fDate :
26-30 Aug. 2002
Firstpage :
1159
Abstract :
Cooperation and learning in multi-agent systems (MAS) is of special interest in DAI. This paper presents a cooperation model called MACM that provides a flexible coordination mechanism to support cooperation and learning in MAS. The learning agent adopts model-free distributed Q-learning. By using projection method, the distributed Q-learning algorithm needs less storage space for the Q-table than the classical Q-learning.
Keywords :
distributed algorithms; learning (artificial intelligence); multi-agent systems; DAI; MACM; MAS; Q-table; cooperation; distributed Q-learning algorithm; distributed artificial intelligence; flexible coordination mechanism; learning; model-free distributed Q-learning; multi-agent system; reinforcement learning; Artificial intelligence; Bayesian methods; Centralized control; Computer aided instruction; Control systems; Councils; Game theory; Intelligent agent; Learning; Multiagent systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing, 2002 6th International Conference on
Print_ISBN :
0-7803-7488-6
Type :
conf
DOI :
10.1109/ICOSP.2002.1179995
Filename :
1179995
Link To Document :
بازگشت