Revert unneeded changes back to master

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

 from mlagents.trainers.trainer.rl_trainer import RLTrainer
 from mlagents.trainers.policy import Policy
 from mlagents.trainers.policy.tf_policy import TFPolicy
-from mlagents.trainers.ppo.optimizer_tf import PPOOptimizer
+from mlagents.trainers.ppo.optimizer import PPOOptimizer
 from mlagents.trainers.trajectory import Trajectory
 from mlagents.trainers.behavior_id_utils import BehaviorIdentifiers
 from mlagents.trainers.settings import TrainerSettings, PPOSettings, FrameworkType

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

             name="old_probabilities",
         )
 
-        # Break old log log_probs into separate branches
+        # Break old log probs into separate branches
         old_log_prob_branches = ModelUtils.break_into_branches(
             self.all_old_log_probs, self.policy.act_size
         )

ml-agents/mlagents/trainers/saver/saver.py

         pass
 
     @abc.abstractmethod
-    def save_checkpoint(self, behavior_name: str, step: int) -> str:
+    def save_checkpoint(self, brain_name: str, step: int) -> str:
-        :param behavior_name: Behavior name of behavior to be trained
+        :param brain_name: Brain name of brain to be trained
-    def export(self, output_filepath: str, behavior_name: str) -> None:
+    def export(self, output_filepath: str, brain_name: str) -> None:
-        Saves the serialized model, given a path and behavior name.
+        Saves the serialized model, given a path and brain name.
-        :param behavior_name: Behavior name of behavior to be trained.
+        :param brain_name: Brain name of brain to be trained.
         """
         pass
 

ml-agents/mlagents/trainers/saver/tf_saver.py

             with self.policy.graph.as_default():
                 self.tf_saver = tf.train.Saver(max_to_keep=self._keep_checkpoints)
 
-    def save_checkpoint(self, behavior_name: str, step: int) -> str:
-        checkpoint_path = os.path.join(self.model_path, f"{behavior_name}-{step}")
+    def save_checkpoint(self, brain_name: str, step: int) -> str:
+        checkpoint_path = os.path.join(self.model_path, f"{brain_name}-{step}")
         # Save the TF checkpoint and graph definition
         if self.graph:
             with self.graph.as_default():
                     self.graph, self.model_path, "raw_graph_def.pb", as_text=False
                 )
         # also save the policy so we have optimized model files for each checkpoint
-        self.export(checkpoint_path, behavior_name)
+        self.export(checkpoint_path, brain_name)
-    def export(self, output_filepath: str, behavior_name: str) -> None:
+    def export(self, output_filepath: str, brain_name: str) -> None:
-            self.model_path, output_filepath, behavior_name, self.graph, self.sess
+            self.model_path, output_filepath, brain_name, self.graph, self.sess
         )
 
     def initialize_or_load(self, policy: Optional[TFPolicy] = None) -> None:
             self._load_graph(policy, self.model_path, reset_global_steps=reset_steps)
         else:
             policy.initialize()
-
         TFPolicy.broadcast_global_variables(0)
 
     def _load_graph(

ml-agents/mlagents/trainers/tests/test_ppo.py

 
 from mlagents.trainers.trainer.rl_trainer import RLTrainer
 from mlagents.trainers.ppo.trainer import PPOTrainer, discount_rewards
-from mlagents.trainers.ppo.optimizer_tf import PPOOptimizer
+from mlagents.trainers.ppo.optimizer import PPOOptimizer
 from mlagents.trainers.policy.tf_policy import TFPolicy
 from mlagents.trainers.agent_processor import AgentManagerQueue
 from mlagents.trainers.tests import mock_brain as mb

ml-agents/mlagents/trainers/tests/test_reward_signals.py

 import mlagents.trainers.tests.mock_brain as mb
 from mlagents.trainers.policy.tf_policy import TFPolicy
 from mlagents.trainers.sac.optimizer import SACOptimizer
-from mlagents.trainers.ppo.optimizer_tf import PPOOptimizer
+from mlagents.trainers.ppo.optimizer import PPOOptimizer
 from mlagents.trainers.tests.test_simple_rl import PPO_CONFIG, SAC_CONFIG
 from mlagents.trainers.settings import (
     GAILSettings,

ml-agents/mlagents/trainers/tests/test_saver.py

 from mlagents.trainers.policy.tf_policy import TFPolicy
 from mlagents.trainers.tests import mock_brain as mb
 from mlagents.trainers.tests.test_nn_policy import create_policy_mock
-from mlagents.trainers.ppo.optimizer_tf import PPOOptimizer
+from mlagents.trainers.ppo.optimizer import PPOOptimizer
 
 
 def test_register(tmp_path):

ml-agents/mlagents/trainers/tf/models.py

         :param action_masks: The mask for the logits. Must be of dimension [None x total_number_of_action]
         :param action_size: A list containing the number of possible actions for each branch
         :return: The action output dimension [batch_size, num_branches], the concatenated
-            normalized log_probs (after softmax)
-        and the concatenated normalized log log_probs
+            normalized probs (after softmax)
+        and the concatenated normalized log probs
         """
         branch_masks = ModelUtils.break_into_branches(action_masks, action_size)
         raw_probs = [