远程经验协调
Remote Empirical Coordination
摘要：
我们应用框架的不完善的经验协调的两个节点设置的第一个节点的行动$X$没有直接观察到，但通过$L$代理观察独立受损的测量$\hat X$的行动。这些$L$代理使用对它们全部可用的速率受限通信来帮助第二节点生成动作$Y$，以便建立期望的协调行为。当$L<\infty$，我们证明，它足以$R_i\geq I\left(\hat X;\hat{Y}\right)$至少一个代理，而$L\longrightarrow\infty$，我们表明，它足以$R_i\geq I\left(\hat X;\hat Y|X\right)$的所有代理，其中$\hat Y$是一个随机变量，使$X-\hat X-\hat Y$和$\|p_{X,\hat Y}\left(x,y\right)-p_{X,Y}\left(x,y\right)\|_{TV}\leq Δ$（$Δ$是预先指定的保真度）。
英文摘要：
We apply the framework of imperfect empirical coordination to a two-node setup where the action $X$ of the first node is not observed directly but via $L$ agents who observe independently impaired measurements $\hat X$ of the action. These $L$ agents, using a rate-limited communication that is available to all of them, help the second node to generate the action $Y$ in order to establish the desired coordinated behaviour. When $L<\infty$, we prove that it suffices $R_i\geq I\left(\hat X;\hat{Y}\right)$ for at least one agent whereas for $L\longrightarrow\infty$, we show that it suffices $R_i\geq I\left(\hat X;\hat Y|X\right)$ for all agents where $\hat Y$ is a random variable such that $X-\hat X-\hat Y$ and $\|p_{X,\hat Y}\left(x,y\right)-p_{X,Y}\left(x,y\right)\|_{TV}\leq Δ$ ( $Δ$ is the pre-specified fidelity).
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。
