# Value Alignment Problem
📗 Player reports threshold \(x_{1}, x_{2}, ...\):
📗 Distance function \(\rho\):
📗 Report function \(z_{i}\):
📗 The average report is: 0
📗 Receiver learns threshold \(\theta\): 0
Log-likehood for different values of \(\theta\):
Reported preferences:
📗 Domain: \(a\) = , \(b\) =
📗 Number of samples of \(\left(y, y', z\right)\):
📗 Number of values of \(\theta\):