DocumentCode
1983898
Title
Fuzzy multi-agent cooperative Q-learning
Author
Gu, Dongbing ; Hu, Huosheng
Author_Institution
Dept. of Comput. Sci., Essex Univ., Colchester, UK
fYear
2005
fDate
27 June-3 July 2005
Abstract
This paper presents a cooperative reinforcement learning algorithm of multi-agent systems. The cooperative behaviour is established within a leader-following framework. Specifically, the cooperative dynamics is modelled as a Stackelberg game. Based on the equilibrium definition of the Stackelberg game, a leader-following Q-learning algorithm is developed. The algorithm is generalised over continuous state space by using fuzzy logic.
Keywords
fuzzy logic; learning (artificial intelligence); multi-agent systems; Stackelberg game; fuzzy logic; leader-following algorithm; multiagent cooperative Q-learning; reinforcement learning; Computer science; Function approximation; Fuzzy logic; Fuzzy systems; Game theory; Learning; Multiagent systems; Orbital robotics; Service robots; State-space methods;
fLanguage
English
Publisher
ieee
Conference_Titel
Information Acquisition, 2005 IEEE International Conference on
Print_ISBN
0-7803-9303-1
Type
conf
DOI
10.1109/ICIA.2005.1635080
Filename
1635080
Link To Document