[skip ci] fix first summary statement output

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

         The reward signal generators must be updated in this method at their own pace.
         """
         self.cumulative_returns_since_policy_update.clear()
+        super()._update_policy()
 
         # Make sure batch_size is a multiple of sequence length. During training, we
         # will need to reshape the data into a batch_size x sequence_length tensor.
             for stat, val in update_stats.items():
                 self._stats_reporter.add_stat(stat, val)
 
-        super()._update_policy()
         self._clear_update_buffer()
 
     def create_policy(self, brain_parameters: BrainParameters) -> TFPolicy:

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

         """
         Uses demonstration_buffer to update model.
         """
-        # increment steps when training instead of when generating from environment
+        self._maybe_write_summary(self.get_step + self.trainer_parameters["buffer_size"])
-        self._maybe_write_summary(self.get_step + self.trainer_parameters["buffer_size"])
 
     def _increment_step(self, n_steps: int, name_behavior_id: str) -> None:
         """
         write the summary. This logic ensures summaries are written on the update step and not in between.
         :param step_after_process: the step count after processing the next trajectory.
         """
-        if step_after_process >= self.next_summary_step and self.get_step != 0:
+        if step_after_process >= self.next_summary_step:
             self._write_summary(self.next_summary_step)
 
     def advance(self) -> None: