Pontryagin-Differentiable-Programming icon indicating copy to clipboard operation
Pontryagin-Differentiable-Programming copied to clipboard

Published 20 hours ago • verified publisher icon wanxinjin

The learning rate of the inverse KKT method in the code is inconsistent with that in the paper.

Open beijiguang94 opened this issue 1 year ago • 2 comments

hi @wanxinjin. I noticed that in the paper the learning rate for PDP, inverse KKT, and neural policy cloning methods in imitation learning was set to $\eta=10^{-4}$. But in scripts like "cartpole_inverseKKT.py", the parameter lr equals 1e-7. Why so?

beijiguang94 avatar Oct 19 '23 04:10 beijiguang94