replace step with get step in tc

ml-agents/mlagents/trainers/trainer_controller.py

     def reset_env_if_ready(self, env: EnvManager) -> None:
         # Get the sizes of the reward buffers.
         reward_buff = {k: list(t.reward_buffer) for (k, t) in self.trainers.items()}
-        curr_step = {k: int(t.step) for (k, t) in self.trainers.items()}
+        curr_step = {k: int(t.get_step) for (k, t) in self.trainers.items()}
         max_step = {k: int(t.get_max_steps) for (k, t) in self.trainers.items()}
         # Attempt to increment the lessons of the brains who
         # were ready.