Title :
A Study of Multiagent Reinforcement Learning based on Quantum Theory
Author :
Xiangping, Meng ; Yuzhen, Pi ; Quande, Yuan ; Ying, Pan
Author_Institution :
Dept. of Electr. Eng., Changchun Inst. of Technol., Changchun
Abstract :
In this paper, we present a novel multiagent reinforcement learning algorithm based on Q-learning and quantum theory. As in reinforcement learning algorithm, when the number of agents or/and agent´s action is large enough, all of the action selection methods will be failed: the speed of learning is decreased sharply, we try to combine the quantum theory with Q-learning, hoping that the problem will be resolved with our proposed.
Keywords :
learning (artificial intelligence); multi-agent systems; quantum computing; Q-learning; multiagent reinforcement learning; quantum theory; reinforcement learning algorithm; Application software; Autonomous agents; Game theory; Learning; Optimal control; Quantum computing; Quantum mechanics; Space technology; Stochastic processes; Systems engineering and theory; Grover operator; Multiagent; Quantum algorithm; Reinforcement learning; Stochastic games;
Conference_Titel :
Computational Engineering in Systems Applications, IMACS Multiconference on
Conference_Location :
Beijing
Print_ISBN :
7-302-13922-9
Electronic_ISBN :
7-900718-14-1
DOI :
10.1109/CESA.2006.4281965
