update max steps and add config

Project/Assets/ML-Agents/Examples/FPS_Game/Scenes/FPS_Game.unity

       propertyPath: UISlider
       value: 
       objectReference: {fileID: 920197661}
+    - target: {fileID: 6960991000376283046, guid: 1c6bcdaf8b76745d8918fc47c464885e,
+        type: 3}
+      propertyPath: m_BehaviorName
+      value: DodgeBall
+      objectReference: {fileID: 0}
     - target: {fileID: 6960991000376283092, guid: 1c6bcdaf8b76745d8918fc47c464885e,
         type: 3}
       propertyPath: cam
   dodgeBallsListTeamO: []
   dodgeBallsListTeam1: []
   AllBallsList: []
-  MaxEnvironmentSteps: 5000
+  MaxEnvironmentSteps: 25000
 --- !u!1 &1826064871
 GameObject:
   m_ObjectHideFlags: 0
       propertyPath: UISlider
       value: 
       objectReference: {fileID: 920197661}
+    - target: {fileID: 6960991000376283046, guid: 1c6bcdaf8b76745d8918fc47c464885e,
+        type: 3}
+      propertyPath: m_BehaviorName
+      value: DodgeBall
+      objectReference: {fileID: 0}
     - target: {fileID: 6960991000376283092, guid: 1c6bcdaf8b76745d8918fc47c464885e,
         type: 3}
       propertyPath: cam
     - target: {fileID: 9116796388679672956, guid: 1c6bcdaf8b76745d8918fc47c464885e,
         type: 3}
       propertyPath: m_LocalRotation.x
-      value: 0.023514433
+      value: 0.023514416
-      value: -0.0000000052765476
+      value: 3.1894046e-10
-      value: 1.2410933e-10
+      value: -7.5017536e-12
       objectReference: {fileID: 0}
     - target: {fileID: 9116796388679672959, guid: 1c6bcdaf8b76745d8918fc47c464885e,
         type: 3}
   m_PrefabInstance: {fileID: 0}
   m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 8697938321410268827}
-  m_LocalRotation: {x: 1.2410933e-10, y: 0.9997235, z: -0.023514433, w: 0.0000000052765476}
+  m_LocalRotation: {x: -7.5017536e-12, y: 0.9997235, z: -0.023514416, w: -3.1894046e-10}
   m_LocalPosition: {x: 20.4, y: 3.1269999, z: 4.1}
   m_LocalScale: {x: 1, y: 1, z: 1}
   m_Children: []

config/ppo/DodgeBall.yaml

+behaviors:
+  DodgeBall:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 2000000
+    time_horizon: 64
+    summary_freq: 60000
+    threaded: true