Closed Akella17 closed 5 years ago
Because input normalization is computer over all observed trajectories and it would not be possible to recompute it after loading the model.
Oh got it! Did not observe that detail. Thanks for the quick response!!
Is there any reason why we are saving the entire model, rather than its state_dict()?
Also, how do I call the PyBullet (Racecar, Minitaur and Kuka), gym-Classic Control (Pendulum v0), Roboschool envs?
I would like to know why is getattr(get_vec_normalize(envs), 'ob_rms', None) saved along with actor-critc network? line: 154-155, main.py