PhysicsInformedNN Documentation Incorrect on Where Parameters Estimation Params Go

[allen-adastra]

The docs claim that when doing parameter estimation problems w/ additional loss functions, the params should go to the end of $\theta$

By copying the Lorenz attractor example, I was able to show that actually the parameters are going into p. I've put the following print statements:

And we can see that we initialize the params to 1.0:

And we get the following printout

Should the docs be updated, or should this bug be fixed s.t. the parameter estimation params go into \theta?

[ChrisRackauckas]

Yes, the docs should be updated.