Modular Q-learning based multi-agent coo
β
Kui-Hong Park; Yong-Jae Kim; Jong-Hwan Kim
π
Article
π
2001
π
Elsevier Science
π
English
β 532 KB
In a multi-agent system, action selection is important for the cooperation and coordination among agents. As the environment is dynamic and complex, modular Q-learning, which is one of the reinforcement learning schemes, is employed in assigning a proper action to an agent in the multi-agent system.