多Agent系统的理论与技术，为分布式开放系统的分析、设计和实现提供了一条崭新的途径。然而随着相关领域高新技术的迅猛发展，多Agent系统的运行环境日益趋于大型、开放、动态和不确定，迫切需要采用各种智能技术来构建具有自学习能力的Agent，为多Agent系统引入学习机制使其更好地适应复杂环境，从而导致了多Agent系统学习这一新兴研究领域的产生和迅速发展。多Agent系统学习包括采用机器学习等方法从积累的信息或数据中学习用于支持决策的知识，以及为建立多Agent协作、协调和竞争等机制而进行的对策学习。因此，机器学习方法和对策学习方法的研究对多Agent系统学习领域的发展具有非常重要的意义。

-　　The theory and techniques in mufti-agent system can be used as a novel method to analyze, design and implementation distributed open system. However, with the rapidly development of relational fields, the environment where mufti-agent systems operates in becomes more and more large, open, dynamic and uncertain. In order to adapt to complicated environment, it s urgent to introduce learning mechanism into

mufti-agent　system,　and　build　intelligent　agent　with　self-learning　ability　by techniques from artificial intelligence. Learning task of mufti-agent system includes learning knowledge for decision support from data and information accumulated by machine learning methods, and game learning for establishing rules of mufti-agent collaboration,　correspondence and　competition.　Therefore,　researching machine learning and game learning methods is very important to evelopment of mufti-agent system learning.