Merge branch 'master' into asymm-envs

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

         """
         policy = self.trainer.create_policy(parsed_behavior_id, brain_parameters)
         policy.create_tf_graph()
+        policy.initialize_or_load()
         policy.init_load_weights()
         team_id = parsed_behavior_id.team_id
         self.controller.subscribe_team_id(team_id, self)
             internal_trainer_policy = self.trainer.create_policy(
                 parsed_behavior_id, brain_parameters
             )
-            internal_trainer_policy.create_tf_graph()
+            self.trainer.add_policy(parsed_behavior_id, internal_trainer_policy)
             internal_trainer_policy.init_load_weights()
             self.current_policy_snapshot[
                 parsed_behavior_id.brain_name
             self._save_snapshot()  # Need to save after trainer initializes policy
-            self.trainer.add_policy(parsed_behavior_id, internal_trainer_policy)
             self._learning_team = self.controller.get_learning_team
             self.wrapped_trainer_team = team_id
         return policy