hyperparameteers and tweaks

Project/Assets/ML-Agents/Examples/FoodCollector/Prefabs/BattleFoodArea.prefab

   m_Model: {fileID: 11400000, guid: 36ab3e93020504f48858d0856f939685, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
-  m_BehaviorName: FoodCollector
+  m_BehaviorName: BattleFoodCollector
   TeamId: 0
   m_UseChildSensors: 1
   m_UseChildActuators: 1
   m_Model: {fileID: 11400000, guid: 36ab3e93020504f48858d0856f939685, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
-  m_BehaviorName: FoodCollector
+  m_BehaviorName: BattleFoodCollector
   TeamId: 0
   m_UseChildSensors: 1
   m_UseChildActuators: 1
   m_Model: {fileID: 11400000, guid: 36ab3e93020504f48858d0856f939685, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
-  m_BehaviorName: FoodCollector
+  m_BehaviorName: BattleFoodCollector
   TeamId: 0
   m_UseChildSensors: 1
   m_UseChildActuators: 1
   m_Model: {fileID: 11400000, guid: 36ab3e93020504f48858d0856f939685, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
-  m_BehaviorName: FoodCollector
+  m_BehaviorName: BattleFoodCollector
   TeamId: 1
   m_UseChildSensors: 1
   m_UseChildActuators: 1
   m_Model: {fileID: 11400000, guid: 36ab3e93020504f48858d0856f939685, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
-  m_BehaviorName: FoodCollector
+  m_BehaviorName: BattleFoodCollector
   TeamId: 1
   m_UseChildSensors: 1
   m_UseChildActuators: 1
   m_EditorClassIdentifier: 
   food: {fileID: 1699568242032636, guid: b59e4a7fd76af471cadd16e90133a084, type: 3}
   badFood: {fileID: 1853821981215314, guid: 350871b865967466daa1f596193cc22e, type: 3}
-  numFood: 3
+  numFood: 1
   numBadFood: 0
   respawnFood: 1
   range: 45
   m_Model: {fileID: 11400000, guid: 36ab3e93020504f48858d0856f939685, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
-  m_BehaviorName: FoodCollector
+  m_BehaviorName: BattleFoodCollector
   TeamId: 1
   m_UseChildSensors: 1
   m_UseChildActuators: 1
   m_EditorClassIdentifier: 
   agents: []
   listArea: []
-  WinningScore: 3
+  WinningScore: 1
   scoreText: {fileID: 0}
   playerStates: []
 --- !u!1 &7442880647489548527

Project/Assets/ML-Agents/Examples/FoodCollector/Scenes/BattleFood.unity

       objectReference: {fileID: 0}
     - target: {fileID: 4688212428263696, guid: 4a2d272a60b4a453d9ec0f6e5708bd73, type: 3}
       propertyPath: m_RootOrder
-      value: 6
+      value: 5
       objectReference: {fileID: 0}
     - target: {fileID: 4688212428263696, guid: 4a2d272a60b4a453d9ec0f6e5708bd73, type: 3}
       propertyPath: m_LocalEulerAnglesHint.x
       objectReference: {fileID: 0}
     - target: {fileID: 4688212428263696, guid: 4a2d272a60b4a453d9ec0f6e5708bd73, type: 3}
       propertyPath: m_RootOrder
-      value: 7
+      value: 6
       objectReference: {fileID: 0}
     - target: {fileID: 4688212428263696, guid: 4a2d272a60b4a453d9ec0f6e5708bd73, type: 3}
       propertyPath: m_LocalEulerAnglesHint.x
   m_LocalScale: {x: 1, y: 1, z: 1}
   m_Children: []
   m_Father: {fileID: 0}
-  m_RootOrder: 4
+  m_RootOrder: 3
   m_LocalEulerAnglesHint: {x: 0, y: 0, z: 0}
 --- !u!1001 &916917435
 PrefabInstance:
       objectReference: {fileID: 0}
     - target: {fileID: 4688212428263696, guid: 4a2d272a60b4a453d9ec0f6e5708bd73, type: 3}
       propertyPath: m_RootOrder
-      value: 8
+      value: 7
       objectReference: {fileID: 0}
     - target: {fileID: 4688212428263696, guid: 4a2d272a60b4a453d9ec0f6e5708bd73, type: 3}
       propertyPath: m_LocalEulerAnglesHint.x
       objectReference: {fileID: 0}
     - target: {fileID: 4688212428263696, guid: 4a2d272a60b4a453d9ec0f6e5708bd73, type: 3}
       propertyPath: m_RootOrder
-      value: 9
+      value: 8
       objectReference: {fileID: 0}
     - target: {fileID: 4688212428263696, guid: 4a2d272a60b4a453d9ec0f6e5708bd73, type: 3}
       propertyPath: m_LocalEulerAnglesHint.x
       objectReference: {fileID: 0}
     m_RemovedComponents: []
   m_SourcePrefab: {fileID: 100100000, guid: 4a2d272a60b4a453d9ec0f6e5708bd73, type: 3}
---- !u!1 &1574236047
-GameObject:
-  m_ObjectHideFlags: 0
-  m_CorrespondingSourceObject: {fileID: 0}
-  m_PrefabInstance: {fileID: 0}
-  m_PrefabAsset: {fileID: 0}
-  serializedVersion: 6
-  m_Component:
-  - component: {fileID: 1574236049}
-  - component: {fileID: 1574236048}
-  m_Layer: 0
-  m_Name: FoodCollectorSettings
-  m_TagString: Untagged
-  m_Icon: {fileID: 0}
-  m_NavMeshLayer: 0
-  m_StaticEditorFlags: 0
-  m_IsActive: 1
---- !u!114 &1574236048
-MonoBehaviour:
-  m_ObjectHideFlags: 0
-  m_CorrespondingSourceObject: {fileID: 0}
-  m_PrefabInstance: {fileID: 0}
-  m_PrefabAsset: {fileID: 0}
-  m_GameObject: {fileID: 1574236047}
-  m_Enabled: 1
-  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: be4599983abb14917a1c76329db0b6b0, type: 3}
-  m_Name: 
-  m_EditorClassIdentifier: 
-  agents: []
-  listArea: []
-  totalScore: 0
-  scoreText: {fileID: 1086444496}
---- !u!4 &1574236049
-Transform:
-  m_ObjectHideFlags: 0
-  m_CorrespondingSourceObject: {fileID: 0}
-  m_PrefabInstance: {fileID: 0}
-  m_PrefabAsset: {fileID: 0}
-  m_GameObject: {fileID: 1574236047}
-  m_LocalRotation: {x: 0, y: 0, z: 0, w: 1}
-  m_LocalPosition: {x: 0.71938086, y: 0.27357092, z: 4.1970553}
-  m_LocalScale: {x: 1, y: 1, z: 1}
-  m_Children: []
-  m_Father: {fileID: 0}
-  m_RootOrder: 3
-  m_LocalEulerAnglesHint: {x: 0, y: 0, z: 0}
 --- !u!1 &1799584680
 GameObject:
   m_ObjectHideFlags: 0
     - target: {fileID: 224194346362733190, guid: 3ce107b4a79bc4eef83afde434932a68,
         type: 3}
       propertyPath: m_RootOrder
-      value: 5
+      value: 4
       objectReference: {fileID: 0}
     - target: {fileID: 224194346362733190, guid: 3ce107b4a79bc4eef83afde434932a68,
         type: 3}

config/ppo/BattleFoodCollector.yaml

+behaviors:
+  BattleFoodCollector:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+    keep_checkpoints: 5
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: true
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0