Two-Sided Parameter Learning of Role Selections for Efficient Team Formation
Two-Sided Parameter Learning of Role Selections for Efficient Team Formation
复制标题
角色选择的双边参数学习以实现高效的团队组建
DOI：
10.1007/978-3-642-32729-2_9
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Dai Hamada and Toshiharu Sugawara
中科院分区：
文献类型：
--
作者：
Ibuki Kawamata;Fumiaki Tanaka;and Masami Hagiya;Dai Hamada and Toshiharu Sugawara
我们提出了一种学习方法，以确定在面向任务的领域中由自利益主体组成有效团队的适当角色。计算机网络上的服务请求最近一直在迅速增加。为了提高这类系统的性能，如何有效地组建团队来完成任务的问题引起了我们的兴趣。所建议的方法的主要特点是从两方面的观点学习，即，主动组建团队的团队领导或在被请求的团队之一中工作的团队成员。为此，我们向代理引入三个参数，以便它们可以选择作为领导者或成员的角色。然后，代理可以预测应该选择哪些其他代理作为团队成员以及它应该加入哪个团队。我们的实验表明，成功组建团队所获得的效用比传统方法要大得多。我们还进行了一些实验来研究所提出方法的特点。结果表明，agent之间发展了分工合作，减少了决策冲突的机会，发挥了作用，实现了高效的团队形成。
We propose a method of learning to determine appropriate roles for forming efficiently teams by self-interested agents in task-oriented domains. Service requests on computer networks have recently been rapidly increasing. To improve the performance of such systems, issues with efficient team formation to do tasks have attracted our interest. The main feature of the proposed method is learning from two-sided viewpoints, i.e., team leaders who have the initiative to form teams or team members who work in one of the teams that are solicited. For this purpose, we introduce three parameters to agents so that they can select their roles of being a leader or a member. Then, an agent can anticipate what other agents should be selected as team members and what team it should join. Our experiments demonstrated that the amount of utility earned as the result of successful team formation was considerably larger than that with a conventional method. We also conducted a number of experiments to investigate the characteristics of the proposed method. The results revealed that the divisional cooperation between agents was developed, which could reduce the chance of conflicts in decisions to play roles and this achieved efficient team formation.