Comment by nestorD

7 hours ago

It's what put MuJoCo on my radar recently! But I was surprised to not see him do any kind of gradient descent to optimize his hyperparameters. MuJoCo has a JAX backend so it should be fairly straightforward.

I'm pretty sure he has used gradient descent in previous videos to optimize systems, maybe this time it was just easier to hand tune rather than set up an optimization feedback harness around MuJoCo.