fixed more ci problems/removed self.policies

ml-agents/mlagents/trainers/rl_trainer.py

         """
         policy = self.create_policy(brain_parameters)
         self.policy = policy
-        self.policies[brain_parameters.brain_name] = policy
+        # self.policies[brain_parameters.brain_name] = policy
 
     def advance(self):
         """

ml-agents/mlagents/trainers/trainer.py

         self.summary_writer = tf.summary.FileWriter(self.summary_path)
         self._reward_buffer: Deque[float] = deque(maxlen=reward_buff_cap)
         self.policy: TFPolicy
-        self.policies: Dict[str, TFPolicy] = {}
         self.step: int = 0
 
     def check_param_keys(self):
         """
         Creates policy
         """
-        raise UnityTrainerException("The update_model method was not implemented.")
+        raise UnityTrainerException("The create_policy method was not implemented.")
+
+    def add_policy(self, brain_parameters: BrainParameters) -> None:
+        """
+        Adds policy to trainer
+        """
+        raise UnityTrainerException("The add_policy method was not implemented.")
-        Gets policy from trainers list of policies
+        Gets policy from trainer
-        return self.policies[brain_name]
+        return self.policy
 
     def advance(self) -> None:
         pass

ml-agents/mlagents/trainers/trainer_controller.py

         :param resampling_interval: Specifies number of simulation steps after which reset parameters are resampled.
         """
         self.trainers: Dict[str, Trainer] = {}
-        self.multi_trainers: Dict[str, Trainer] = {}
         self.brain_name_to_identifier: Dict[str, Set] = defaultdict(set)
         self.trainer_factory = trainer_factory
         self.model_path = model_path