Actor is fine regardless of state_dim

[jimzers]

KinovaGrasping/gym-kinova-gripper/DDPGfD.py

Line 94 in 5333116

return self.actor(state).cpu().data.numpy().flatten()

Works with both observation shapes of 82 and 26.

The input into the actor: (1, 82) and (1, 26).

Expected behavior: should throw an error when the wrong observation shape on the last axis is fed to the agent.

This may highlight deeper issues in our networks?