Beyond curse of dimensionality

We implement column-by-column calculation for any model in terms of x in general:

from j=1 to n

We use local index number indn around the evaluated point xs[t-1] and estimate

y=xs[t] for this x=xs[t-1] given data of k=x[indn] and k1=x[ind[indn]] when we consider

local policy function interpolation.