博弈生成网络框架及其在关系推理中的应用
A Game Generative Network Framework with its Application to Relationship Inference
摘要：
博弈过程是一个系统，其中一个代理的决策可以影响其他代理的决策。在现实世界中，社会影响和主体之间的关系可能会影响具有博弈行为的主体的决策。反过来，这也给了我们机会，通过观察他们在博弈过程中的相互作用，从代理中挖掘这些信息。在本文中，我们提出了一个游戏生成网络（GGN）的框架，利用真实的游戏结果和理想的游戏模型之间的偏差，生成网络的游戏过程，这打开了一扇大门，了解代理与游戏行为的网络挖掘方法。我们说明了如何应用GGN推断与游戏行为的代理之间的隐藏关系，并进行团队游戏的实验作为一个具体的例子。实验结果表明，我们提出的框架可以揭示隐藏的代理在这样的游戏关系。
英文摘要：
A game process is a system where the decisions of one agent can influence the decisions of other agents. In the real world, social influences and relationships between agents may influence the decision makings of agents with game behaviors. And in turn, this also gives us the opportunity to mine such information from agents by the observed interactions of them in a game process. In this paper, we propose a Game Generative Network (GGN) framework that utilizes the deviation between the real game outcome and the ideal game model to generate networks for game processes, which opens a door for understanding agents with game behaviors by network mining approaches. We illustrate how to apply GGNs to infer the hidden relationships between agents with game behaviors and conduct experiments on team games as a concrete example. Experimental results demonstrate that our proposed framework can reveal the hidden relationships of agents in such games.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
