[skip ci] moving step increment to trainer from environment for sac

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()
+        self._maybe_write_summary(
+            self.get_step + self.trainer_parameters["buffer_size"]
+        )
+        self._increment_step(self.trainer_parameters["buffer_size"], self.brain_name)
 
         # 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.

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

         """
 
         self.cumulative_returns_since_policy_update.clear()
+        self._maybe_write_summary(
+            self.get_step
+            + self.trainer_parameters["num_update"]
+            * self.trainer_parameters["batch_size"]
+        )
+        self._increment_step(
+            self.trainer_parameters["num_update"]
+            * self.trainer_parameters["batch_size"],
+            self.brain_name,
+        )
+
-        num_updates = self.trainer_parameters["num_update"]
-        for _ in range(num_updates):
+        for _ in range(self.trainer_parameters["num_update"]):
             logger.debug("Updating SAC policy at step {}".format(self.step))
             buffer = self.update_buffer
             if (

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

         """
         Uses demonstration_buffer to update model.
         """
-        self._maybe_write_summary(self.get_step + self.trainer_parameters["buffer_size"])
-        self._increment_step(self.trainer_parameters["buffer_size"], self.brain_name)
+        pass
 
     def _increment_step(self, n_steps: int, name_behavior_id: str) -> None:
         """