Title :
Selecting Behavior on Repeated Local Effect Functions
Author :
Igoshi, Kazuho ; Miura, Takao
Author_Institution :
Dept.of Electr. & Electr. Eng., HOSEI Univ., Tokyo, Japan
fDate :
Aug. 31 2010-Sept. 3 2010
Abstract :
In this study, under multi-agent environment, we introduce a notion of probabilistic Nash equilibrium into reinforcement learning method. Here we take an approach of mixed Nash strategy based on correlated technique in terms of Local Effect functions. We examine some experiment results to show some ideal properties for cooperative approach.
Keywords :
learning (artificial intelligence); multi-agent systems; probability; correlated technique; local effect functions; multiagent environment; probabilistic Nash equilibrium; reinforcement learning method; repeated local effect functions; selecting behavior; Local Effect Games; Multi-Agent System; Nash equilibrium;
Conference_Titel :
Web Intelligence and Intelligent Agent Technology (WI-IAT), 2010 IEEE/WIC/ACM International Conference on
Conference_Location :
Toronto, ON
Print_ISBN :
978-1-4244-8482-9
Electronic_ISBN :
978-0-7695-4191-4
DOI :
10.1109/WI-IAT.2010.166
