Curriculum learning reward thresholding bug fix (#1141)

6 年前 · 29084e77
--- a/UnitySDK/Assets/ML-Agents/Examples/WallJump/Scenes/WallJump.unity
+++ b/UnitySDK/Assets/ML-Agents/Examples/WallJump/Scenes/WallJump.unity
 --- !u!104 &2
 RenderSettings:
  m_ObjectHideFlags: 0
-  serializedVersion: 9
+  serializedVersion: 8
  m_Fog: 0
  m_FogColor: {r: 0.5, g: 0.5, b: 0.5, a: 1}
  m_FogMode: 3
  m_CustomReflection: {fileID: 0}
  m_Sun: {fileID: 0}
  m_IndirectSpecularColor: {r: 0, g: 0, b: 0, a: 1}
-  m_UseRadianceAmbientProbe: 0
 --- !u!157 &3
 LightmapSettings:
  m_ObjectHideFlags: 0
    m_EnableBakedLightmaps: 1
    m_EnableRealtimeLightmaps: 1
  m_LightmapEditorSettings:
-    serializedVersion: 10
+    serializedVersion: 9
-    m_AtlasSize: 1024
+    m_TextureWidth: 1024
+    m_TextureHeight: 1024
    m_AO: 0
    m_AOMaxDistance: 1
    m_CompAOExponent: 1
    debug:
      m_Flags: 0
  m_NavMeshData: {fileID: 0}
--- !u!114 &5623674
-MonoBehaviour:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 0}
-  m_Enabled: 1
-  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 35813a1be64e144f887d7d5f15b963fa, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  m_EditorClassIdentifier: 
-  brain: {fileID: 681747651}
 --- !u!1001 &117944611
 Prefab:
  m_ObjectHideFlags: 0
    m_RemovedComponents: []
  m_ParentPrefab: {fileID: 100100000, guid: 54e3af627216447f790531de496099f0, type: 2}
  m_IsPrefabParent: 0
--- !u!114 &208265148
+--- !u!114 &188528345
 MonoBehaviour:
  m_ObjectHideFlags: 0
  m_PrefabParentObject: {fileID: 0}
  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 8b23992c8eb17439887f5e944bf04a40, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  m_Script: {fileID: 11500000, guid: 35813a1be64e144f887d7d5f15b963fa, type: 3}
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  broadcast: 1
-  graphModel: {fileID: 4900000, guid: fae11f80dd25b4bc4918ce5223fd8e5b, type: 3}
-  graphScope: SmallWallBrain
-  graphPlaceholders: []
-  BatchSizePlaceholderName: batch_size
-  VectorObservationPlacholderName: vector_observation
-  RecurrentInPlaceholderName: recurrent_in
-  RecurrentOutPlaceholderName: recurrent_out
-  VisualObservationPlaceholderName: []
-  ActionPlaceholderName: action
-  PreviousActionPlaceholderName: prev_action
-  brain: {fileID: 681747651}
+  brain: {fileID: 532941885}
 --- !u!1001 &236193370
 Prefab:
  m_ObjectHideFlags: 0
    m_RemovedComponents: []
  m_ParentPrefab: {fileID: 100100000, guid: 54e3af627216447f790531de496099f0, type: 2}
  m_IsPrefabParent: 0
--- !u!114 &471621718
-MonoBehaviour:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 0}
-  m_Enabled: 1
-  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 943466ab374444748a364f9d6c3e2fe2, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  m_EditorClassIdentifier: 
-  broadcast: 1
-  brain: {fileID: 681747651}
 --- !u!1 &532941884
 GameObject:
  m_ObjectHideFlags: 0
    vectorActionSpaceType: 0
  brainType: 0
  CoreBrains:
-  - {fileID: 1580680280}
-  - {fileID: 612829772}
-  - {fileID: 1933570538}
-  - {fileID: 963476526}
-  instanceID: 81918
+  - {fileID: 1906993920}
+  - {fileID: 1504875100}
+  - {fileID: 188528345}
+  - {fileID: 0}
+  instanceID: 12522
 --- !u!4 &532941886
 Transform:
  m_ObjectHideFlags: 0
  m_Father: {fileID: 1574236049}
  m_RootOrder: 1
  m_LocalEulerAnglesHint: {x: 0, y: 0, z: 0}
--- !u!114 &612829772
-MonoBehaviour:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 0}
-  m_Enabled: 1
-  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 943466ab374444748a364f9d6c3e2fe2, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  m_EditorClassIdentifier: 
-  broadcast: 1
-  brain: {fileID: 0}
 --- !u!1 &681747649
 GameObject:
  m_ObjectHideFlags: 0
    vectorActionSpaceType: 0
  brainType: 0
  CoreBrains:
-  - {fileID: 2020471305}
-  - {fileID: 471621718}
-  - {fileID: 5623674}
-  - {fileID: 208265148}
-  instanceID: 81924
+  - {fileID: 2038042629}
+  - {fileID: 882328761}
+  - {fileID: 1525918528}
+  - {fileID: 0}
+  instanceID: 12530
 --- !u!1001 &684891805
 Prefab:
  m_ObjectHideFlags: 0
  m_Father: {fileID: 0}
  m_RootOrder: 0
  m_LocalEulerAnglesHint: {x: 29.773, y: -69.171005, z: -29.985}
+--- !u!114 &882328761
+MonoBehaviour:
+  m_ObjectHideFlags: 0
+  m_PrefabParentObject: {fileID: 0}
+  m_PrefabInternal: {fileID: 0}
+  m_GameObject: {fileID: 0}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: 943466ab374444748a364f9d6c3e2fe2, type: 3}
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  m_EditorClassIdentifier: 
+  broadcast: 1
+  brain: {fileID: 681747651}
 --- !u!1001 &922229267
 Prefab:
  m_ObjectHideFlags: 0
    m_RemovedComponents: []
  m_ParentPrefab: {fileID: 100100000, guid: 54e3af627216447f790531de496099f0, type: 2}
  m_IsPrefabParent: 0
--- !u!114 &963476526
-MonoBehaviour:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 0}
-  m_Enabled: 1
-  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 8b23992c8eb17439887f5e944bf04a40, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  m_EditorClassIdentifier: 
-  broadcast: 1
-  graphModel: {fileID: 4900000, guid: fae11f80dd25b4bc4918ce5223fd8e5b, type: 3}
-  graphScope: BigWallBrain
-  graphPlaceholders: []
-  BatchSizePlaceholderName: batch_size
-  VectorObservationPlacholderName: vector_observation
-  RecurrentInPlaceholderName: recurrent_in
-  RecurrentOutPlaceholderName: recurrent_out
-  VisualObservationPlaceholderName: []
-  ActionPlaceholderName: action
-  PreviousActionPlaceholderName: prev_action
-  brain: {fileID: 532941885}
 --- !u!1 &1009000883
 GameObject:
  m_ObjectHideFlags: 0
    m_RemovedComponents: []
  m_ParentPrefab: {fileID: 100100000, guid: 54e3af627216447f790531de496099f0, type: 2}
  m_IsPrefabParent: 0
+--- !u!114 &1504875100
+MonoBehaviour:
+  m_ObjectHideFlags: 0
+  m_PrefabParentObject: {fileID: 0}
+  m_PrefabInternal: {fileID: 0}
+  m_GameObject: {fileID: 0}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: 943466ab374444748a364f9d6c3e2fe2, type: 3}
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  m_EditorClassIdentifier: 
+  broadcast: 1
+  brain: {fileID: 0}
+--- !u!114 &1525918528
+MonoBehaviour:
+  m_ObjectHideFlags: 0
+  m_PrefabParentObject: {fileID: 0}
+  m_PrefabInternal: {fileID: 0}
+  m_GameObject: {fileID: 0}
+  m_Enabled: 1
+  m_EditorHideFlags: 0
+  m_Script: {fileID: 11500000, guid: 35813a1be64e144f887d7d5f15b963fa, type: 3}
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  m_EditorClassIdentifier: 
+  brain: {fileID: 681747651}
 --- !u!1001 &1543174177
 Prefab:
  m_ObjectHideFlags: 0
  m_Script: {fileID: 11500000, guid: 50b93afe82bc647b581a706891913e7f, type: 3}
  m_Name: 
  m_EditorClassIdentifier: 
-  maxSteps: 10000
+  maxSteps: 0
  trainingConfiguration:
    width: 80
    height: 80
  gravityMultiplier: 2.5
  agentJumpVelocity: 777
  agentJumpVelocityMaxChange: 10
--- !u!114 &1580680280
-MonoBehaviour:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 0}
-  m_Enabled: 1
-  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 41e9bda8f3cf1492fa74926a530f6f70, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
-  m_EditorClassIdentifier: 
-  broadcast: 1
-  keyContinuousPlayerActions:
-  - key: 97
-    index: 0
-    value: -1
-  - key: 100
-    index: 0
-    value: 1
-  - key: 119
-    index: 1
-    value: 1
-  - key: 115
-    index: 1
-    value: -1
-  - key: 32
-    index: 2
-    value: 1
-  axisContinuousPlayerActions: []
-  discretePlayerActions:
-  - key: 119
-    branchIndex: 0
-    value: 1
-  - key: 115
-    branchIndex: 0
-    value: 2
-  - key: 100
-    branchIndex: 1
-    value: 2
-  - key: 97
-    branchIndex: 1
-    value: 1
-  - key: 32
-    branchIndex: 3
-    value: 1
-  brain: {fileID: 532941885}
 --- !u!1001 &1839574406
 Prefab:
  m_ObjectHideFlags: 0
    m_RemovedComponents: []
  m_ParentPrefab: {fileID: 100100000, guid: 54e3af627216447f790531de496099f0, type: 2}
  m_IsPrefabParent: 0
--- !u!114 &1933570538
+--- !u!114 &1906993920
 MonoBehaviour:
  m_ObjectHideFlags: 0
  m_PrefabParentObject: {fileID: 0}
  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 35813a1be64e144f887d7d5f15b963fa, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  m_Script: {fileID: 11500000, guid: 41e9bda8f3cf1492fa74926a530f6f70, type: 3}
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  broadcast: 1
+  keyContinuousPlayerActions:
+  - key: 97
+    index: 0
+    value: -1
+  - key: 100
+    index: 0
+    value: 1
+  - key: 119
+    index: 1
+    value: 1
+  - key: 115
+    index: 1
+    value: -1
+  - key: 32
+    index: 2
+    value: 1
+  axisContinuousPlayerActions: []
+  discretePlayerActions:
+  - key: 119
+    branchIndex: 0
+    value: 1
+  - key: 115
+    branchIndex: 0
+    value: 2
+  - key: 100
+    branchIndex: 1
+    value: 2
+  - key: 97
+    branchIndex: 1
+    value: 1
+  - key: 32
+    branchIndex: 3
+    value: 1
  brain: {fileID: 532941885}
 --- !u!1 &1955352159
 GameObject:
    m_RemovedComponents: []
  m_ParentPrefab: {fileID: 100100000, guid: 54e3af627216447f790531de496099f0, type: 2}
  m_IsPrefabParent: 0
--- !u!114 &2020471305
+--- !u!114 &2038042629
 MonoBehaviour:
  m_ObjectHideFlags: 0
  m_PrefabParentObject: {fileID: 0}
  m_EditorHideFlags: 0
  m_Script: {fileID: 11500000, guid: 41e9bda8f3cf1492fa74926a530f6f70, type: 3}
-  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
+  m_Name: (Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)(Clone)
  m_EditorClassIdentifier: 
  broadcast: 1
  keyContinuousPlayerActions:
--- a/config/curricula/push-block/PushBlockBrain.json
+++ b/config/curricula/push-block/PushBlockBrain.json
 {
    "measure" : "reward",
    "thresholds" : [0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75],
-    "min_lesson_length" : 2,
+    "min_lesson_length" : 100,
    "signal_smoothing" : true, 
    "parameters" : 
    {
--- a/config/curricula/test/TestBrain.json
+++ b/config/curricula/test/TestBrain.json
 {
    "measure" : "reward",
    "thresholds" : [10, 20, 50],
-    "min_lesson_length" : 3,
+    "min_lesson_length" : 100,
    "signal_smoothing" : true, 
    "parameters" : 
    {
--- a/config/curricula/wall-jump/BigWallBrain.json
+++ b/config/curricula/wall-jump/BigWallBrain.json
 {
    "measure" : "progress",
    "thresholds" : [0.1, 0.3, 0.5],
-    "min_lesson_length" : 2,
+    "min_lesson_length": 100,
    "signal_smoothing" : true, 
    "parameters" : 
    {
--- a/config/curricula/wall-jump/SmallWallBrain.json
+++ b/config/curricula/wall-jump/SmallWallBrain.json
 {
    "measure" : "progress",
    "thresholds" : [0.1, 0.3, 0.5],
-    "min_lesson_length" : 2,
+    "min_lesson_length": 100,
    "signal_smoothing" : true, 
    "parameters" : 
    {
--- a/docs/Migrating.md
+++ b/docs/Migrating.md
  [trainer_config.yaml](../config/trainer_config.yaml). An example of passing
  a trainer configuration to `mlagents-learn` is shown above.
 * The environment name is now passed through the `--env` option.
-* Curriculum files must now be placed into a folder and be named appropriately.
-  Refer to the
-  [Curriculum training documentation](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Training-Curriculum-Learning.md)
-  for more information.
+* Curriculum learning has been changed. Refer to the
+    [curriculum learning documentation](Training-Curriculum-Learning.md)
+    for detailed information. In summary:
+  * Curriculum files for the same environment must now be placed into a folder.
+    Each curriculum file should be named after the brain whose curriculum it
+    specifies.
+  * `min_lesson_length` now specifies the minimum number of episodes in a lesson
+    and affects reward thresholding.
+  * It is no longer necessary to specify the `Max Steps` of the Academy to use
+    curriculum learning.

 ## Migrating from ML-Agents toolkit v0.3 to v0.4

--- a/docs/Training-Curriculum-Learning.md
+++ b/docs/Training-Curriculum-Learning.md
 {
    "measure" : "progress",
    "thresholds" : [0.1, 0.3, 0.5],
-    "min_lesson_length" : 2,
+    "min_lesson_length" : 100,
    "signal_smoothing" : true,
    "parameters" :
    {
  * `progress` - Uses ratio of steps/max_steps.
 * `thresholds` (float array) - Points in value of `measure` where lesson should
  be increased.
-* `min_lesson_length` (int) - How many times the progress measure should be
-  reported before incrementing the lesson.
+* `min_lesson_length` (int) - The minimum number of episodes that should be
+  completed before the lesson can change. If `measure` is set to `reward`, the
+  average cumulative reward of the last `min_lesson_length` episodes will be
+  used to determine if the lesson should change. Must be nonnegative.
+
+  __Important__: the average reward that is compared to the thresholds is
+  different than the mean reward that is logged to the console. For example,
+  if `min_lesson_length` is `100`, the lesson will increment after the average
+  cumulative reward of the last `100` episodes exceeds the current threshold.
+  The mean reward logged to the console is dictated by the `summary_freq`
+  parameter in the
+  [trainer configuration file](Training-ML-Agents.md#training-config-file).
 * `signal_smoothing` (true/false) - Whether to weight the current progress
  measure by previous values.
  * If `true`, weighting will be 0.75 (new) 0.25 (old).
 mlagents-learn config/trainer_config.yaml --curriculum=curricula/wall-jump/ --run-id=wall-jump-curriculum --train
 ```

-We can then keep track of the current
-lessons and progresses via TensorBoard.
+We can then keep track of the current lessons and progresses via TensorBoard.
--- a/ml-agents/mlagents/trainers/curriculum.py
+++ b/ml-agents/mlagents/trainers/curriculum.py
 import os
 import json
+import math

 from .exception import CurriculumError

        """
        Initializes a Curriculum object.
        :param location: Path to JSON defining curriculum.
-        :param default_reset_parameters: Set of reset parameters for environment.
+        :param default_reset_parameters: Set of reset parameters for
+               environment.
-        self.lesson_length = 0
        self.max_lesson_num = 0
        self.measure = None
        self._lesson_num = 0
            raise CurriculumError(
                'The file {0} could not be found.'.format(location))
        except UnicodeDecodeError:
-            raise CurriculumError('There was an error decoding {}'.format(location))
+            raise CurriculumError('There was an error decoding {}'
+                                  .format(location))
-                                                "{1} field.".format(location, key))
+                                      "{1} field."
+                                      .format(location, key))
+        self.min_lesson_length = self.data['min_lesson_length']
        self.max_lesson_num = len(self.data['thresholds'])

        parameters = self.data['parameters']
                raise CurriculumError(
                    'The parameter {0} in Curriculum {1} must have {2} values '
                    'but {3} were found'.format(key, location,
-                                                self.max_lesson_num + 1, len(parameters[key])))
+                                                self.max_lesson_num + 1,
+                                                len(parameters[key])))

    @property
    def lesson_num(self):
    def lesson_num(self, lesson_num):
-        self.lesson_length = 0
-    def increment_lesson(self, progress):
+    def increment_lesson(self, measure_val):
-        :param progress: Measure of progress (either reward or percentage steps completed).
+        :param measure_val: Measure of progress (either reward or percentage
+               steps completed).
+        :return Whether the lesson was incremented.
-        if self.data is None or progress is None:
-            return
+        if not self.data or not measure_val or math.isnan(measure_val):
+            return False
-            progress = self.smoothing_value * 0.25 + 0.75 * progress
-            self.smoothing_value = progress
-        self.lesson_length += 1
+            measure_val = self.smoothing_value * 0.25 + 0.75 * measure_val
+            self.smoothing_value = measure_val
-            if ((progress > self.data['thresholds'][self.lesson_num]) and
-                    (self.lesson_length > self.data['min_lesson_length'])):
-                self.lesson_length = 0
+            if measure_val > self.data['thresholds'][self.lesson_num]:
                self.lesson_num += 1
                config = {}
                parameters = self.data['parameters']
                            .format(self._brain_name,
                                    self.lesson_num,
-                                    ', '.join([str(x) + ' -> ' + str(config[x]) for x in config])))
+                                    ', '.join([str(x) + ' -> ' + str(config[x])
+                                        for x in config])))
+                return True
+        return False
-        :param lesson: The lesson you want to get the config of. If None, the current lesson is returned.
+        :param lesson: The lesson you want to get the config of. If None, the
+               current lesson is returned.
-        if self.data is None:
+        if not self.data:
            return {}
        if lesson is None:
            lesson = self.lesson_num
--- a/ml-agents/mlagents/trainers/meta_curriculum.py
+++ b/ml-agents/mlagents/trainers/meta_curriculum.py


 class MetaCurriculum(object):
-    """A MetaCurriculum holds curriculums. Each curriculum is associated to a particular
-    brain in the environment.
+    """A MetaCurriculum holds curriculums. Each curriculum is associated to a
+    particular brain in the environment.
    """

    def __init__(self, curriculum_folder, default_reset_parameters):
                brain_name = curriculum_filename.split('.')[0]
                curriculum_filepath = \
                    os.path.join(curriculum_folder, curriculum_filename)
-                curriculum = Curriculum(curriculum_filepath, default_reset_parameters)
+                curriculum = Curriculum(curriculum_filepath,
+                                        default_reset_parameters)
-                if any([(parameter in curriculum.get_config().keys()) for parameter in used_reset_parameters]):
+                if any([(parameter in curriculum.get_config().keys())
+                    for parameter in used_reset_parameters]):
                    logger.warning('Two or more curriculums will '
                                'attempt to change the same reset '
                                'parameter. The result will be '
        for brain_name, lesson in lesson_nums.items():
            self.brains_to_curriculums[brain_name].lesson_num = lesson

-    def increment_lessons(self, progresses):
-        """Increments all the lessons of all the curriculums in this MetaCurriculum.
+    def _lesson_ready_to_increment(self, brain_name, reward_buff_size):
+        """Determines whether the curriculum of a specified brain is ready
+        to attempt an increment.
-            progresses (dict): A dict of brain name to progress.
+            brain_name (str): The name of the brain whose curriculum will be
+                checked for readiness.
+            reward_buff_size (int): The size of the reward buffer of the trainer
+                that corresponds to the specified brain.
+
+        Returns:
+            Whether the curriculum of the specified brain should attempt to
+            increment its lesson.
-        for brain_name, progress in progresses.items():
-            self.brains_to_curriculums[brain_name].increment_lesson(progress)
+        return reward_buff_size >= (self.brains_to_curriculums[brain_name]
+                                        .min_lesson_length)
+
+    def increment_lessons(self, measure_vals, reward_buff_sizes=None):
+        """Attempts to increments all the lessons of all the curriculums in this
+        MetaCurriculum. Note that calling this method does not guarantee the
+        lesson of a curriculum will increment. The lesson of a curriculum will
+        only increment if the specified measure threshold defined in the
+        curriculum has been reached and the minimum number of episodes in the
+        lesson have been completed.
+
+        Args:
+            measure_vals (dict): A dict of brain name to measure value.
+            reward_buff_sizes (dict): A dict of brain names to the size of their
+                corresponding reward buffers.
+
+        Returns:
+            A dict from brain name to whether that brain's lesson number was
+            incremented.
+        """
+        ret = {}
+        if reward_buff_sizes:
+            for brain_name, buff_size in reward_buff_sizes.items():
+                if self._lesson_ready_to_increment(brain_name, buff_size):
+                    measure_val = measure_vals[brain_name]
+                    ret[brain_name] = (self.brains_to_curriculums[brain_name]
+                                           .increment_lesson(measure_val))
+        else:
+            for brain_name, measure_val in measure_vals.items():
+                ret[brain_name] = (self.brains_to_curriculums[brain_name]
+                                       .increment_lesson(measure_val))
+        return ret
-        """Sets all the curriculums in this meta curriculum to a specified lesson number.
+        """Sets all the curriculums in this meta curriculum to a specified
+        lesson number.

        Args:
            lesson_num (int): The lesson number which all the curriculums will


    def get_config(self):
-        """Get the combined configuration of all curriculums in this MetaCurriculum.
+        """Get the combined configuration of all curriculums in this
+        MetaCurriculum.

        Returns:
            A dict from parameter to value.
--- a/ml-agents/mlagents/trainers/ppo/trainer.py
+++ b/ml-agents/mlagents/trainers/ppo/trainer.py

 import logging
 import os
+from collections import deque

 import numpy as np
 import tensorflow as tf
 class PPOTrainer(Trainer):
    """The PPOTrainer is an implementation of the PPO algorithm."""

-    def __init__(self, sess, brain, trainer_parameters, training, seed, run_id):
+    def __init__(self, sess, brain, reward_buff_cap, trainer_parameters, training, seed, run_id):
        """
        Responsible for collecting experiences and training PPO model.
        :param sess: Tensorflow session.

        self.training_buffer = Buffer()
        self.cumulative_rewards = {}
+        self._reward_buffer = deque(maxlen=reward_buff_cap)
        self.episode_steps = {}
        self.summary_path = trainer_parameters['summary_path']
        if not os.path.exists(self.summary_path):
        :return: the step count of the trainer
        """
        return self.step
+
+    @property
+    def reward_buffer(self):
+        """
+        Returns the reward buffer. The reward buffer contains the cumulative
+        rewards of the most recent episodes completed by agents using this
+        trainer.
+        :return: the reward buffer.
+        """
+        return self._reward_buffer

    def increment_step_and_update_last_reward(self):
        """
                if info.local_done[l]:
                    self.stats['cumulative_reward'].append(
                        self.cumulative_rewards.get(agent_id, 0))
+                    self.reward_buffer.appendleft(self.cumulative_rewards.get(agent_id, 0))
                    self.stats['episode_length'].append(
                        self.episode_steps.get(agent_id, 0))
                    self.cumulative_rewards[agent_id] = 0
--- a/ml-agents/mlagents/trainers/trainer.py
+++ b/ml-agents/mlagents/trainers/trainer.py
        """
        Responsible for collecting experiences and training a neural network model.
        :param sess: Tensorflow session.
-        :param  trainer_parameters: The parameters for the trainer (dictionary).
+        :param trainer_parameters: The parameters for the trainer (dictionary).
        :param training: Whether the trainer is set for training.
        """
        self.sess = sess
--- a/ml-agents/mlagents/trainers/trainer_controller.py
+++ b/ml-agents/mlagents/trainers/trainer_controller.py
 class TrainerController(object):
    def __init__(self, env_path, run_id, save_freq, curriculum_folder,
                 fast_simulation, load, train, worker_id, keep_checkpoints,
-                 lesson, seed, docker_target_name, trainer_config_path,
-                 no_graphics):
+                 lesson, seed, docker_target_name,
+                 trainer_config_path, no_graphics):
        """
        :param env_path: Location to the environment executable to be loaded.
        :param run_id: The sub-directory name for model and summary statistics
                                                                       'name as the Brain '
                                                                       'whose curriculum it defines.')

-    def _get_progresses(self):
+    def _get_measure_vals(self):
-            brain_names_to_progresses = {}
+            brain_names_to_measure_vals = {}
-                    in self.meta_curriculum.brains_to_curriculums.items():
-                if curriculum.measure == "progress":
-                    progress = (self.trainers[brain_name].get_step /
-                                self.trainers[brain_name].get_max_steps)
-                    brain_names_to_progresses[brain_name] = progress
-                elif curriculum.measure == "reward":
-                    progress = self.trainers[brain_name].get_last_reward
-                    brain_names_to_progresses[brain_name] = progress
-            return brain_names_to_progresses
+                in self.meta_curriculum.brains_to_curriculums.items():
+                if curriculum.measure == 'progress':
+                    measure_val = (self.trainers[brain_name].get_step /
+                        self.trainers[brain_name].get_max_steps)
+                    brain_names_to_measure_vals[brain_name] = measure_val
+                elif curriculum.measure == 'reward':
+                    measure_val = np.mean(self.trainers[brain_name]
+                                          .reward_buffer)
+                    brain_names_to_measure_vals[brain_name] = measure_val
+            return brain_names_to_measure_vals
        else:
            return None

                    trainer_parameters[k] = trainer_config[_brain_key][k]
            trainer_parameters_dict[brain_name] = trainer_parameters.copy()
        for brain_name in self.env.external_brain_names:
-            if trainer_parameters_dict[brain_name]['trainer'] == "imitation":
+            if trainer_parameters_dict[brain_name]['trainer'] == 'imitation':
-            elif trainer_parameters_dict[brain_name]['trainer'] == "ppo":
+            elif trainer_parameters_dict[brain_name]['trainer'] == 'ppo':
+                    self.meta_curriculum
+                        .brains_to_curriculums[brain_name]
+                        .min_lesson_length if self.meta_curriculum else 0,
                    trainer_parameters_dict[brain_name],
                    self.train_model, self.seed, self.run_id)
            else:
                                            'permissions are set correctly.'
                                            .format(model_path))

-    def _increment_lessons_and_reset_env(self):
-        """Increments the lessons of curriculums if there is a metacurriculum
-        and resets the environment.
+    def _reset_env(self):
+        """Resets the environment.

        Returns:
            A Data structure corresponding to the initial reset state of the
-            self.meta_curriculum.increment_lessons(self._get_progresses())
            return self.env.reset(config=self.meta_curriculum.get_config(),
                                  train_mode=self.fast_simulation)
        else:
            else:
                sess.run(init)
            global_step = 0  # This is only for saving the model
-            curr_info = self._increment_lessons_and_reset_env()
+            curr_info = self._reset_env()
            if self.train_model:
                for brain_name, trainer in self.trainers.items():
                    trainer.write_tensorboard_text('Hyperparameters',
                           for k, t in self.trainers.items()]) \
-                        or not self.train_model:
-                    if self.env.global_done:
-                        curr_info = self._increment_lessons_and_reset_env()
+                      or not self.train_model:
+                    if self.meta_curriculum:
+                        # Get the sizes of the reward buffers.
+                        reward_buff_sizes = {k:len(t.reward_buffer) \
+                                            for (k,t) in self.trainers.items()}
+                        # Attempt to increment the lessons of the brains who
+                        # were ready.
+                        lessons_incremented = \
+                            self.meta_curriculum.increment_lessons(
+                                self._get_measure_vals(),
+                                reward_buff_sizes=reward_buff_sizes)
+
+                    # If any lessons were incremented or the environment is
+                    # ready to be reset
+                    if (self.meta_curriculum
+                            and any(lessons_incremented.values())
+                        or self.env.global_done):
+                        curr_info = self._reset_env()
+                        for brain_name, changed in lessons_incremented.items():
+                            if changed:
+                                self.trainers[brain_name].reward_buffer.clear()
+
                    # Decide and take an action
                    take_action_vector, \
                    take_action_memories, \
--- a/ml-agents/tests/trainers/test_curriculum.py
+++ b/ml-agents/tests/trainers/test_curriculum.py
    curriculum.lesson_num = 1
    assert curriculum.lesson_num == 1

-    curriculum.increment_lesson(10)
+    assert not curriculum.increment_lesson(10)
-    curriculum.increment_lesson(30)
-    curriculum.increment_lesson(30)
-    assert curriculum.lesson_num == 1
-    assert curriculum.lesson_length == 3
+    assert curriculum.increment_lesson(30)
+    assert curriculum.lesson_num == 2
-    curriculum.increment_lesson(30)
-    assert curriculum.lesson_length == 0
+    assert not curriculum.increment_lesson(30)
+
+    assert curriculum.increment_lesson(10000)
+    assert curriculum.lesson_num == 3


@patch('builtins.open', new_callable=mock_open, read_data=dummy_curriculum_json_str)
--- a/ml-agents/tests/trainers/test_meta_curriculum.py
+++ b/ml-agents/tests/trainers/test_meta_curriculum.py


@pytest.fixture
-def progresses():
+def measure_vals():
+
+
+@pytest.fixture
+def reward_buff_sizes():
+    return {'Brain1' : 7, 'Brain2' : 8}


@patch('mlagents.trainers.Curriculum.get_config', return_value={})

@patch('mlagents.trainers.Curriculum')
@patch('mlagents.trainers.Curriculum')
-def test_increment_lessons(curriculum_a, curriculum_b, progresses):
+def test_increment_lessons(curriculum_a, curriculum_b, measure_vals):
-    meta_curriculum.increment_lessons(progresses)
+    meta_curriculum.increment_lessons(measure_vals)
+
+
+@patch('mlagents.trainers.Curriculum')
+@patch('mlagents.trainers.Curriculum')
+def test_increment_lessons_with_reward_buff_sizes(curriculum_a, curriculum_b,
+                                                  measure_vals,
+                                                  reward_buff_sizes):
+    curriculum_a.min_lesson_length = 5
+    curriculum_b.min_lesson_length = 10
+    meta_curriculum = MetaCurriculumTest({'Brain1' : curriculum_a,
+                                          'Brain2' : curriculum_b})
+
+    meta_curriculum.increment_lessons(measure_vals,
+                                      reward_buff_sizes=reward_buff_sizes)
+
+    curriculum_a.increment_lesson.assert_called_with(0.2)
+    curriculum_b.increment_lesson.assert_not_called()


@patch('mlagents.trainers.Curriculum')