Learning to Infer Structures of Network Games
Learning to Infer Structures of Network Games
复制标题
DOI：
10.48550/arxiv.2206.08119
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Emanuele Rossi;Federico Monti;Yan Leng;Michael M. Bronstein;Xiaowen Dong
中科院分区：
文献类型：
--
作者：
Emanuele Rossi;Federico Monti;Yan Leng;Michael M. Bronstein;Xiaowen Dong
一组个人或组织之间的战略互动可以被建模为网络上的游戏，其中玩家的收益不仅取决于他们的行为，还取决于他们的邻居。从观察到的博弈结果（均衡行动）推断网络结构是一个重要的问题，在经济学和社会科学中有许多潜在的应用。现有的方法大多需要与游戏相关的效用函数的知识，这在现实世界的场景中往往是不现实的。我们采用了一个类似变压器的架构，它正确地解释了问题的对称性，并在没有明确的效用函数知识的情况下，学习了从均衡行动到游戏网络结构的映射。我们使用合成和真实世界的数据在三种不同类型的网络游戏上测试了我们的方法，并证明了它在网络结构推理方面的有效性和优于现有方法的上级性能。
Strategic interactions between a group of individuals or organisations can be modelled as games played on networks, where a player's payoff depends not only on their actions but also on those of their neighbours. Inferring the network structure from observed game outcomes (equilibrium actions) is an important problem with numerous potential applications in economics and social sciences. Existing methods mostly require the knowledge of the utility function associated with the game, which is often unrealistic to obtain in real-world scenarios. We adopt a transformer-like architecture which correctly accounts for the symmetries of the problem and learns a mapping from the equilibrium actions to the network structure of the game without explicit knowledge of the utility function. We test our method on three different types of network games using both synthetic and real-world data, and demonstrate its effectiveness in network structure inference and superior performance over existing methods.