While , some algorithms of machine learning are introduced to get the intelligence of the individual of hfutagent which makes individual skills in the robocup . finally , we realize the multi - agent cooperation mechanism using the knoledge of soccer experts . in our system , a typical cooperation method in robocup called sbsp is used , and we explains how to use reinforcement learning method to reach the goal of local cooperation , and the offense and defense strategy system is build by decision - theoretic 在本文中，首先介绍了典型的agent结构和mas模型和仿真机器人足球的一些主要模型：设计了一个分层的agent结构? hfutagent ，通过机器学习算法实现了agent的个体智能；最后结合足球领域专家的知识实现了agent间的协作，其中使用了robocup中一个典型的协作方法- sbsp ，设计了一个通过强化学习的方法来达到agent之间的局部协作，把基于效用的对策论方法引入了hfutteam的进攻体系和防守体系中。
Secondly , the mixed h2 / h control is formulated as a game problem of incomplete information , a suboptimal 2x2 non - zero game model is constructed , where two channels are chose as players and h2 and h control are pure strategies , and an algorithm for mixed h2 / h control , which is based on the nash ' s bargaining theory , is derived to achieve the nash equilibrium point . finally , handling stability , ride comfort and steering handiness are related with vehicle suspension system and electrical power steering 其次，基于对策论把h _ 2 h _混合控制问题抽象为两个对局者信息不完全情况下的非零和博弈模型，在以次优范数值构造的2x2非零和博弈模型中把两类通道作为参加博弈的两方，以h _ 2和h _控制方案作为两种纯策略，基于纳什谈判解原理设计出求解h _ 2 h _混合控制问题纳什均衡点的算法。
The multi - agent systems investigate how to coordinate the intelligent behavious of a collection of autonomous agents , where no global control , no globally consistent knowledge , no globally shared goals . there is possibility for real competition among agents . their nature is a complex dynamic evolving course . here conflict is inevitable , so many corresponding specially solving methods appeared . drawing lessons from game theory - based negotiation research , the paper describes the negotiation methods having been presented , introduces the game theory - based negotiation research mainly 多主体系统研究如何协调一组主体的智能行动，这里没有全局控制，没有全局一致性知识，没有全局共有目标，可能这更符合多个主体间的实际竞争情况，其本质是复杂的动力学演变过程.在这里，冲突不可避免，从而出现了许多解决特定冲突的协商算法，文中叙述已有的协商方法，着重介绍基于对策论的协商研究
With analyzing the aviation anti - submarine warfare and establishing the model of efficiency evaluating about the aviation anti - submarine warfare , the game theory and optimal control theory were applied in researching the efficiency of aviation anti - submarine warfare constrained by the submarine c velocity and energy 通过对航空兵应召反潜搜索的分析，建立应召反潜搜索效能评枯模型，并应用对策论与最优控制理论对模型进行分析，研究在潜艇速度和电黄双约束条件下，影响搜索效能的关键因素，为航空兵战术决策提供依据。
Many researchers presented corresponding models for multi - agent negotiation framework . rosenschein introduced a negotiation model using the idea of game theory , sycara constructed a model based on the labour and capital negotiation , kraus created a common negotiation framework considering sociality and cooperation in negotiation , sandholm gave a commitment based negotiation mechanism . another model given by jennings took the changing of the mental state and joint - commitment into account 许多学者提出了一些理论和方法，包括rosenschein等人的基于对策论的理性协商理论， r . smith等人提出的合同网理论， sycara的以劳资谈判为背景的协商理论， kraus的最佳平衡协商理论， sandholm的多agent核结盟理论以及jenning等人基于协商中思维状态变迁的联合承诺理论等等。
