AI 中文总结
该研究针对全局博弈提出网络共同学习概念，发现其在二维网格等网络中可实现，在直线等存在信息瓶颈的网络中无法实现，均衡中仅安全行动留存。
AI 中文摘要
我们研究全局博弈，其中主体在有利状态下与社交网络邻居进行局部协调。行动前，主体学习网络距离$r$内所有主体的私人信号。随着$r$增大，每个主体都能知晓状态，但有效协调取决于高阶信念，而高阶信念由网络的几何结构塑造。我们引入网络共同学习（common learning的网络类似物），证明当相邻主体的观测值相差多个信号时（如二维网格）可实现该学习，而存在信息瓶颈的网络（如直线）无法实现，此时均衡中仅安全行动留存。
英文摘要
We study global games in which agents coordinate locally, with their social network neighbors, contingent on a favorable state. Before acting, agents learn the private signals of all agents within network distance $r$. As $r$ grows, every agent learns the state, but efficient coordination depends on higher-order beliefs, which are shaped by the geometry of the network. We introduce network common learning, a network analogue of common learning, and show that it is attained when neighboring agents' observations differ by many signals, as on the two-dimensional grid, but fails on networks with informational bottlenecks, such as the line, where only the safe action survives in equilibrium.
