Gradient based policy optimisation. about pilco HOT 4 CLOSED

Gradients are computed and used in L-BFGS-B. This is the whole point of using TensorFlow. Perhaps this is not immediately obvious when examining the code, because the gradient computation is handled via GPflow.

from pilco.

Hello,
Does it mean using numerical calculated gradient, not analytically calculated gradient?

from pilco.

It’s neither, it’s via automatic differentiation.

from pilco.

I thought the minimize() automatically calculate the gradient using the finite-difference method.
(In case of scipy.optimize.minimize;
"If None or False, the gradient will be estimated using 2-point finite difference estimation with an absolute step size.")
https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.minimize.html

Anyway, I'll study TensorFlow and GPflow.
Thanks!

from pilco.