recalculation of reward after action update

[soldierofhell]

Hi @homangab,
Thanks for the effort to boost the performance of CEM optimization in the right (gradient) direction.
However reading the code I don't see (probably should be somwhere here) an update of rewards after the actions are updated by optimizer.

gradcem/mpc/gradcem.py

Line 44 in 02a8b36

returns = self.env.rollout(actions)

should be calculated once again. Am I wrong?

Regards,