Fix comments

ml-agents/mlagents/trainers/trainer/rl_trainer.py

     def advance(self) -> None:
         """
         Steps the trainer, taking in trajectories and updates if ready.
-        Will block and wait if there are no trajectories.
+        Will block and wait briefly if there are no trajectories.
-                # We grab at most the maximum length of the queue.
-                # This ensures that even if the queue is being filled faster than it is
-                # being emptied, the trajectories in the queue are on-policy.
                 try:
                     t = traj_queue.get(0.05)
                     self._process_trajectory(t)

ml-agents/mlagents/trainers/trainer_controller.py

                         "Environment/Lesson", curr.lesson_num
                     )
 
-        # # Advance trainers. This can be done in a separate loop in the future.
-        # with hierarchical_timer("trainer_advance"):
-        #     for trainer in self.trainers.values():
-        #         trainer.advance()
-
         return num_steps
 
     def trainer_update_func(self, trainer: Trainer) -> None: