摘要
Reinforcement learning allows agent that has no knowledge of an environment to cooperate more efficacious each other. This paper presents an approach for developing multi-agent reinforcement learning systems based on equation principle. The experiment shows agent can produces the desired behavior under all kinds of situation.
Reinforcement learning allows agent that has no knowledge of an environment to cooperate more efficacious each other. This paper presents an approach for developing multi-agent reinforcement learning systems based on equation principle. The experiment shows agent can produces the desired behavior under all kinds of situation.
出处
《计算机科学》
CSCD
北大核心
2003年第4期16-18,共3页
Computer Science
基金
国防科工委"十五"攻关项目基金"智能机器人"
