摘要
本文从协作模型和研究方法两个角度考察了多智能体协作技术的发展 ,认为是外在的理性形式化模型和内在的对策和学习机制是多智能体协作技术的两个重要方面 .
The technology of multiagent cooperation is introduced in this paper from the cooperation model and mechanism, and draw a conclusion that the formal model and the games and learinging mechanism are two crucial facets in research multiagent cooperation. The future research of the two parts and the application of multiagent coopetation is prospected in the end.
出处
《信息与控制》
CSCD
北大核心
2001年第4期337-342,共6页
Information and Control
基金
国家重点科学基金支持 ( 39930 0 70 )
关键词
多智能体协作
自协调模型
递归建模
MARKOV对策
智能控制
multiagent cooperation, self coordination model, recusive modeling, markov Game, reinforcement Learning
