Merge branch 'master' into develop-var-len-obs-feature

.github/workflows/pytest.yml

 jobs:
   pytest:
     runs-on: ubuntu-latest
+    env:
+        TEST_ENFORCE_BUFFER_KEY_TYPES: 1
     strategy:
       matrix:
         python-version: [3.6.x, 3.7.x, 3.8.x]
         python -m pip install --progress-bar=off -e ./ml-agents
         python -m pip install --progress-bar=off -r test_requirements.txt
         python -m pip install --progress-bar=off -e ./gym-unity
+        python -m pip install --progress-bar=off -e ./ml-agents-plugin-examples
     - name: Save python dependencies
       run: |
         pip freeze > pip_versions-${{ matrix.python-version }}.txt

.yamato/com.unity.ml-agents-performance.yml

 test_editors:
   - version: 2019.4
-  - version: 2020.1
   - version: 2020.2
 ---
 {% for editor in test_editors %}

.yamato/com.unity.ml-agents-test.yml

     enableCodeCoverage: !!bool true
     testProject: DevProject
     enableNoDefaultPackages: !!bool true
-  - version: 2020.1
-    enableCodeCoverage: !!bool true
-    testProject: DevProject
-    enableNoDefaultPackages: !!bool true
   - version: 2020.2
     enableCodeCoverage: !!bool true
     testProject: DevProject

.yamato/compressed-sensor-test.yml

     - .yamato/standalone-build-test.yml#test_linux_standalone_{{ editor.version }}
   triggers:
     cancel_old_ci: true
+    {% if editor.extra_test == "sensor" %}
     expression: |
       (pull_request.target eq "master" OR
       pull_request.target match "release.+") AND
       pull_request.changes.any match "Project/**" OR
-      pull_request.changes.any match "ml-agents/**" OR
+      pull_request.changes.any match "ml-agents/tests/yamato/**" OR
+    {% endif %}
 {% endfor %}

.yamato/gym-interface-test.yml

     - .yamato/standalone-build-test.yml#test_linux_standalone_{{ editor.version }}
   triggers:
     cancel_old_ci: true
+    {% if editor.extra_test == "gym" %}
     expression: |
       (pull_request.target eq "master" OR
       pull_request.target match "release.+") AND
-      pull_request.changes.any match "ml-agents/**" OR
+      pull_request.changes.any match "ml-agents/tests/yamato/**" OR
+    {% endif %}
 {% endfor %}

.yamato/python-ll-api-test.yml

     - .yamato/standalone-build-test.yml#test_linux_standalone_{{ editor.version }}
   triggers:
     cancel_old_ci: true
+    {% if editor.extra_test == "llapi" %}
     expression: |
       (pull_request.target eq "master" OR
       pull_request.target match "release.+") AND
-      pull_request.changes.any match "ml-agents/**" OR
+      pull_request.changes.any match "ml-agents/tests/yamato/**" OR
+    {% endif %}
 {% endfor %}

.yamato/test_versions.metafile

 # List of editor versions for standalone-build-test and its dependencies.
-# csharp_backcompat_version is used in training-int-tests to determine the
-# older package version to run the backwards compat tests against.
+# We always run training-int-tests for all versions of the editor
+# For each "other" test, we only run it against a single version of the
+# editor to reduce the number of yamato jobs
-    csharp_backcompat_version: 1.0.0
+    extra_test: llapi
-    csharp_backcompat_version: 1.0.0
-  - version: 2020.1
-    csharp_backcompat_version: 1.0.0
+    extra_test: gym
-    # 2020.2 moved the AssetImporters namespace
-    # but we didn't handle this until 1.2.0
-    csharp_backcompat_version: 1.2.0
+    extra_test: sensor

Project/Assets/ML-Agents/Editor/Tests/StandaloneBuildTest.cs

                 scenes,
                 outputPath,
                 buildTarget,
-                BuildOptions.None
+                BuildOptions.Development
             );
             var isOk = buildResult.summary.result == BuildResult.Succeeded;
             var error = "";

Project/Assets/ML-Agents/Examples/3DBall/Prefabs/3DBall.prefab

   m_BrainParameters:
     VectorObservationSize: 8
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 2
+      BranchSizes: 
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: 3DBall
   TeamId: 0

Project/Assets/ML-Agents/Examples/3DBall/Prefabs/3DBallHardNew.prefab

   m_Name: 
   m_EditorClassIdentifier: 
   m_BrainParameters:
-    vectorObservationSize: 5
-    numStackedVectorObservations: 9
-    vectorActionSize: 02000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 1
-  m_Model: {fileID: 11400000, guid: 27d49984757ed46b181090a532ef48e5, type: 3}
-  m_InferenceDevice: 0
+    VectorObservationSize: 0
+    NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 2
+      BranchSizes: 
+    VectorActionSize: 02000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 1
+    hasUpgradedBrainParametersWithActionSpec: 1
+  m_Model: {fileID: 11400000, guid: d179c44c147aa4ffbbb725f009eca3b8, type: 3}
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 1
 --- !u!114 &114466000339026140
 MonoBehaviour:
   m_ObjectHideFlags: 0
   agentParameters:
     maxStep: 0
   hasUpgradedFromAgentParameters: 1
-  maxStep: 5000
+  MaxStep: 5000
   ball: {fileID: 1142513601053358}
 --- !u!114 &8193279139064749781
 MonoBehaviour:
   m_EditorClassIdentifier: 
   DecisionPeriod: 5
   TakeActionsBetweenDecisions: 1
-  offsetStep: 0
 --- !u!114 &7923264721978289873
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1978072206102878
 GameObject:
   m_ObjectHideFlags: 0

Project/Assets/ML-Agents/Examples/3DBall/Prefabs/Visual3DBall.prefab

   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 2
+      BranchSizes: 
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: Visual3DBall
   TeamId: 0

Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DHardAgent.cs

 using Unity.MLAgents;
 using Unity.MLAgents.Actuators;
 using Unity.MLAgents.Sensors;
+using Unity.MLAgents.Sensors.Reflection;
 
 public class Ball3DHardAgent : Agent
 {
         SetResetParameters();
     }
 
-    public override void CollectObservations(VectorSensor sensor)
+    [Observable(numStackedObservations: 9)]
+    Vector2 Rotation
-        sensor.AddObservation(gameObject.transform.rotation.z);
-        sensor.AddObservation(gameObject.transform.rotation.x);
-        sensor.AddObservation((ball.transform.position - gameObject.transform.position));
+        get
+        {
+            return new Vector2(gameObject.transform.rotation.z, gameObject.transform.rotation.x);
+        }
+    }
+
+    [Observable(numStackedObservations: 9)]
+    Vector3 PositionDelta
+    {
+        get
+        {
+            return ball.transform.position - gameObject.transform.position;
+        }
     }
 
     public override void OnActionReceived(ActionBuffers actionBuffers)

Project/Assets/ML-Agents/Examples/Basic/Prefabs/Basic.prefab

   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: Basic
   TeamId: 0

Project/Assets/ML-Agents/Examples/Bouncer/Prefabs/Environment.prefab

   m_Name: 
   m_EditorClassIdentifier: 
   m_BrainParameters:
-    vectorObservationSize: 6
-    numStackedVectorObservations: 3
-    vectorActionSize: 03000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 1
+    VectorObservationSize: 6
+    NumStackedVectorObservations: 3
+    m_ActionSpec:
+      m_NumContinuousActions: 3
+      BranchSizes: 
+    VectorActionSize: 03000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 1
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114878620968301562
 MonoBehaviour:
   m_ObjectHideFlags: 0
   agentParameters:
     maxStep: 0
   hasUpgradedFromAgentParameters: 1
-  maxStep: 0
+  MaxStep: 0
   target: {fileID: 1160631129428284}
   bodyObject: {fileID: 1680588139522898}
   strength: 500
   m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1680588139522898
 GameObject:
   m_ObjectHideFlags: 0

Project/Assets/ML-Agents/Examples/Crawler/Prefabs/CrawlerBase.prefab

   m_BrainParameters:
     VectorObservationSize: 32
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 20
+      BranchSizes: 
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: 
   TeamId: 0

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

     VectorActionSpaceType: 1
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 3210b528a2bc44a86bd6bd1d571070f8, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: FoodCollector
   TeamId: 0
     VectorActionSpaceType: 1
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 3210b528a2bc44a86bd6bd1d571070f8, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: FoodCollector
   TeamId: 0
     VectorActionSpaceType: 1
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 3210b528a2bc44a86bd6bd1d571070f8, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: FoodCollector
   TeamId: 0
     VectorActionSpaceType: 1
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 3210b528a2bc44a86bd6bd1d571070f8, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: FoodCollector
   TeamId: 0
     VectorActionSpaceType: 1
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 3210b528a2bc44a86bd6bd1d571070f8, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: FoodCollector
   TeamId: 0

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

     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 75910f45f20be49b18e2b95879a217b2, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: GridFoodCollector
   TeamId: 0
     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 75910f45f20be49b18e2b95879a217b2, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: GridFoodCollector
   TeamId: 0
     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 75910f45f20be49b18e2b95879a217b2, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: GridFoodCollector
   TeamId: 0
     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 75910f45f20be49b18e2b95879a217b2, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: GridFoodCollector
   TeamId: 0
     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 75910f45f20be49b18e2b95879a217b2, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: GridFoodCollector
   TeamId: 0

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

     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: ec4b31b5d66ca4e51ae3ac41945facb2, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: VisualFoodCollector
   TeamId: 0
     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: ec4b31b5d66ca4e51ae3ac41945facb2, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: VisualFoodCollector
   TeamId: 0
     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: ec4b31b5d66ca4e51ae3ac41945facb2, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: VisualFoodCollector
   TeamId: 0
     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: ec4b31b5d66ca4e51ae3ac41945facb2, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: VisualFoodCollector
   TeamId: 0

Project/Assets/ML-Agents/Examples/GridWorld/Prefabs/Area.prefab

   m_Name: 
   m_EditorClassIdentifier: 
   m_BrainParameters:
-    vectorObservationSize: 0
-    numStackedVectorObservations: 1
-    vectorActionSize: 05000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 0
+    VectorObservationSize: 0
+    NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 05000000
+    VectorActionSize: 05000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 0
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114650561397225712
 MonoBehaviour:
   m_ObjectHideFlags: 0
   agentParameters:
     maxStep: 0
   hasUpgradedFromAgentParameters: 1
-  maxStep: 100
+  MaxStep: 100
   area: {fileID: 114704252266302846}
   timeBetweenDecisionsAtInference: 0.15
   renderCamera: {fileID: 0}
   m_Width: 84
   m_Height: 64
   m_Grayscale: 0
+  m_ObservationStacks: 1
   m_Compression: 1
 --- !u!114 &7980686505185502968
 MonoBehaviour:
   m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1625008366184734
 GameObject:
   m_ObjectHideFlags: 0
   trueAgent: {fileID: 1488387672112076}
   goalPref: {fileID: 1508142483324970, guid: 1ec4e4e96e7514d45b7ebc3ba5a9a481, type: 3}
   pitPref: {fileID: 1811317785436014, guid: d13ee2db77b3a4dcc8664d2fe2a0f219, type: 3}
+  numberOfObstacles: 1
 --- !u!1 &1656910849934022
 GameObject:
   m_ObjectHideFlags: 0

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

   m_ReflectionIntensity: 1
   m_CustomReflection: {fileID: 0}
   m_Sun: {fileID: 0}
-  m_IndirectSpecularColor: {r: 0.44971228, g: 0.49977815, b: 0.57563734, a: 1}
+  m_IndirectSpecularColor: {r: 0.4497121, g: 0.49977785, b: 0.57563704, a: 1}
   m_UseRadianceAmbientProbe: 0
 --- !u!157 &3
 LightmapSettings:
   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 05000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: GridWorld
   TeamId: 0

Project/Assets/ML-Agents/Examples/Hallway/Prefabs/SymbolFinderArea.prefab

   m_BrainParameters:
     VectorObservationSize: 1
     NumStackedVectorObservations: 3
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 05000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: Hallway
   TeamId: 0

Project/Assets/ML-Agents/Examples/Hallway/Prefabs/VisualSymbolFinderArea.prefab

   m_Name: 
   m_EditorClassIdentifier: 
   m_BrainParameters:
-    vectorObservationSize: 0
-    numStackedVectorObservations: 1
-    vectorActionSize: 05000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 0
+    VectorObservationSize: 0
+    NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 05000000
+    VectorActionSize: 05000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 0
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
-  m_TeamID: 0
-  m_useChildSensors: 1
+  TeamId: 0
+  m_UseChildSensors: 1
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114451776683649118
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Script: {fileID: 11500000, guid: b446afae240924105b36d07e8d17a608, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  maxStep: 3000
+  agentParameters:
+    maxStep: 0
+  hasUpgradedFromAgentParameters: 1
+  MaxStep: 3000
   ground: {fileID: 1625056884785366}
   area: {fileID: 1689874756253538}
   symbolOGoal: {fileID: 1800868804754718}
   m_Script: {fileID: 11500000, guid: 282f342c2ab144bf38be65d4d0c4e07d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  camera: {fileID: 20961984019151212}
-  sensorName: CameraSensor
-  width: 84
-  height: 84
-  grayscale: 0
-  compression: 1
+  m_Camera: {fileID: 20961984019151212}
+  m_SensorName: CameraSensor
+  m_Width: 84
+  m_Height: 84
+  m_Grayscale: 0
+  m_ObservationStacks: 1
+  m_Compression: 1
 --- !u!114 &640264344416331590
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Name: 
   m_EditorClassIdentifier: 
   DecisionPeriod: 6
-  RepeatAction: 1
-  offsetStep: 0
+  TakeActionsBetweenDecisions: 1
 --- !u!1 &1377584197416466
 GameObject:
   m_ObjectHideFlags: 0

Project/Assets/ML-Agents/Examples/Match3/Prefabs/Match3Heuristic.prefab

     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: c34da50737a3c4a50918002b20b2b927, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: Match3SmartHeuristic
   TeamId: 0
   Columns: 8
   NumCellTypes: 6
   NumSpecialTypes: 2
-  RandomSeed: -1
+  RandomSeed: -1
 --- !u!114 &3508723250470608014
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Name: 
   m_EditorClassIdentifier: 
   ActuatorName: Match3 Actuator
+  RandomSeed: -1
-  HeuristicQuality: 0
 --- !u!1 &3508723250774301855
 GameObject:
   m_ObjectHideFlags: 0

Project/Assets/ML-Agents/Examples/Match3/Prefabs/Match3VectorObs.prefab

     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 9e89b8e81974148d3b7213530d00589d, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: Match3VectorObs
   TeamId: 0
   Columns: 8
   NumCellTypes: 6
   NumSpecialTypes: 2
-  RandomSeed: -1
+  RandomSeed: -1
 --- !u!114 &2118285884327540680
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Name: 
   m_EditorClassIdentifier: 
   ActuatorName: Match3 Actuator
+  RandomSeed: -1
-  HeuristicQuality: 0

Project/Assets/ML-Agents/Examples/Match3/Prefabs/Match3VisualObs.prefab

     VectorActionSpaceType: 0
     hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 48d14da88fea74d0693c691c6e3f2e34, type: 3}
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: Match3VisualObs
   TeamId: 0
   Columns: 8
   NumCellTypes: 6
   NumSpecialTypes: 2
-  RandomSeed: -1
+  RandomSeed: -1
 --- !u!114 &3019509692332007783
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Name: 
   m_EditorClassIdentifier: 
   ActuatorName: Match3 Actuator
+  RandomSeed: -1
-  HeuristicQuality: 0

Project/Assets/ML-Agents/Examples/PushBlock/Prefabs/PushBlockArea.prefab

   m_Name: 
   m_EditorClassIdentifier: 
   m_BrainParameters:
-    vectorObservationSize: 0
-    numStackedVectorObservations: 2
-    vectorActionSize: 07000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 0
+    VectorObservationSize: 0
+    NumStackedVectorObservations: 2
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 07000000
+    VectorActionSize: 07000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 0
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114505490781873732
 MonoBehaviour:
   m_ObjectHideFlags: 0
   agentParameters:
     maxStep: 0
   hasUpgradedFromAgentParameters: 1
-  maxStep: 5000
+  MaxStep: 5000
   ground: {fileID: 1500989011945850}
   area: {fileID: 1125452240183160}
   areaBounds:
   m_EditorClassIdentifier: 
   DecisionPeriod: 5
   TakeActionsBetweenDecisions: 1
-  offsetStep: 0
 --- !u!114 &4081319787948195948
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1500989011945850
 GameObject:
   m_ObjectHideFlags: 0

Project/Assets/ML-Agents/Examples/PushBlock/Prefabs/PushBlockVisualArea.prefab

   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 07000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &114812843792483960
 MonoBehaviour:
   m_Width: 84
   m_Height: 84
   m_Grayscale: 0
+  m_ObservationStacks: 1
   m_Compression: 1
 --- !u!114 &9049837659352187721
 MonoBehaviour:

Project/Assets/ML-Agents/Examples/Pyramids/Prefabs/AreaPB.prefab

   m_Name: 
   m_EditorClassIdentifier: 
   m_BrainParameters:
-    vectorObservationSize: 4
-    numStackedVectorObservations: 1
-    vectorActionSize: 05000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 0
+    VectorObservationSize: 4
+    NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 05000000
+    VectorActionSize: 05000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 0
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114937736047215868
 MonoBehaviour:
   m_ObjectHideFlags: 0
   agentParameters:
     maxStep: 0
   hasUpgradedFromAgentParameters: 1
-  maxStep: 5000
+  MaxStep: 5000
   area: {fileID: 1464170487903594}
   areaSwitch: {fileID: 1432086782037750}
   useVectorObs: 1
   m_EditorClassIdentifier: 
   DecisionPeriod: 5
   TakeActionsBetweenDecisions: 1
-  offsetStep: 0
 --- !u!114 &5712624269609438939
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1148882946833254
 GameObject:
   m_ObjectHideFlags: 0

Project/Assets/ML-Agents/Examples/Pyramids/Prefabs/VisualAreaPyramids.prefab

   m_Name: 
   m_EditorClassIdentifier: 
   m_BrainParameters:
-    vectorObservationSize: 0
-    numStackedVectorObservations: 1
-    vectorActionSize: 05000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 0
+    VectorObservationSize: 0
+    NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 05000000
+    VectorActionSize: 05000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 0
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
-  m_TeamID: 0
-  m_useChildSensors: 1
+  TeamId: 0
+  m_UseChildSensors: 1
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114741503533626942
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Script: {fileID: 11500000, guid: b8db44472779248d3be46895c4d562d5, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  maxStep: 5000
+  agentParameters:
+    maxStep: 0
+  hasUpgradedFromAgentParameters: 1
+  MaxStep: 5000
   area: {fileID: 1055559745433172}
   areaSwitch: {fileID: 1212218760704844}
   useVectorObs: 0
   m_Script: {fileID: 11500000, guid: 282f342c2ab144bf38be65d4d0c4e07d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  camera: {fileID: 20712684238256298}
-  sensorName: CameraSensor
-  width: 84
-  height: 84
-  grayscale: 0
-  compression: 1
+  m_Camera: {fileID: 20712684238256298}
+  m_SensorName: CameraSensor
+  m_Width: 84
+  m_Height: 84
+  m_Grayscale: 0
+  m_ObservationStacks: 1
+  m_Compression: 1
 --- !u!114 &9216598927300453297
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Name: 
   m_EditorClassIdentifier: 
   DecisionPeriod: 5
-  RepeatAction: 1
-  offsetStep: 0
+  TakeActionsBetweenDecisions: 1
 --- !u!1 &1747856067778386
 GameObject:
   m_ObjectHideFlags: 0

Project/Assets/ML-Agents/Examples/Reacher/Prefabs/Agent.prefab

   m_Name: 
   m_EditorClassIdentifier: 
   m_BrainParameters:
-    vectorObservationSize: 33
-    numStackedVectorObservations: 1
-    vectorActionSize: 04000000
-    vectorActionDescriptions: []
-    vectorActionSpaceType: 1
+    VectorObservationSize: 33
+    NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 4
+      BranchSizes: 
+    VectorActionSize: 04000000
+    VectorActionDescriptions: []
+    VectorActionSpaceType: 1
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114955921823023820
 MonoBehaviour:
   m_ObjectHideFlags: 0
   agentParameters:
     maxStep: 0
   hasUpgradedFromAgentParameters: 1
-  maxStep: 4000
+  MaxStep: 4000
   pendulumA: {fileID: 1644872085946016}
   pendulumB: {fileID: 1053261483945176}
   hand: {fileID: 1654288206095398}
   m_EditorClassIdentifier: 
   DecisionPeriod: 4
   TakeActionsBetweenDecisions: 1
-  offsetStep: 0
 --- !u!114 &7840105453417110232
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1644872085946016
 GameObject:
   m_ObjectHideFlags: 0

Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/ModelOverrider.cs

         const string k_CommandLineModelOverrideDirectoryFlag = "--mlagents-override-model-directory";
         const string k_CommandLineModelOverrideExtensionFlag = "--mlagents-override-model-extension";
         const string k_CommandLineQuitAfterEpisodesFlag = "--mlagents-quit-after-episodes";
+        const string k_CommandLineQuitAfterSeconds = "--mlagents-quit-after-seconds";
         const string k_CommandLineQuitOnLoadFailure = "--mlagents-quit-on-load-failure";
 
         // The attached Agent
         // Max episodes to run. Only used if > 0
         // Will default to 1 if override models are specified, otherwise 0.
         int m_MaxEpisodes;
+
+        // Deadline - exit if the time exceeds this
+        DateTime m_Deadline = DateTime.MaxValue;
 
         int m_NumSteps;
         int m_PreviousNumSteps;
         void GetAssetPathFromCommandLine()
         {
             var maxEpisodes = 0;
+            var timeoutSeconds = 0;
+
             string[] commandLineArgsOverride = null;
             if (!string.IsNullOrEmpty(debugCommandLineOverride) && Application.isEditor)
             {
                 {
                     Int32.TryParse(args[i + 1], out maxEpisodes);
                 }
+                else if (args[i] == k_CommandLineQuitAfterSeconds && i < args.Length - 1)
+                {
+                    Int32.TryParse(args[i + 1], out timeoutSeconds);
+                }
                 else if (args[i] == k_CommandLineQuitOnLoadFailure)
                 {
                     m_QuitOnLoadFailure = true;
                 m_MaxEpisodes = maxEpisodes > 0 ? maxEpisodes : 1;
                 Debug.Log($"setting m_MaxEpisodes to {maxEpisodes}");
             }
+
+            if (timeoutSeconds > 0)
+            {
+                m_Deadline = DateTime.Now + TimeSpan.FromSeconds(timeoutSeconds);
+                Debug.Log($"setting deadline to {timeoutSeconds} from now.");
+
+            }
         }
 
         void OnEnable()
                     EditorApplication.isPlaying = false;
 #endif
                 }
+                else if (DateTime.Now >= m_Deadline)
+                {
+                    Debug.Log(
+                        $"Deadline exceeded. " +
+                        $"{TotalCompletedEpisodes}/{m_MaxEpisodes} episodes and " +
+                        $"{TotalNumSteps}/{m_MaxEpisodes * m_Agent.MaxStep} steps completed. Exiting.");
+                    Application.Quit(0);
+#if UNITY_EDITOR
+                    EditorApplication.isPlaying = false;
+#endif
+                }
+
             m_NumSteps++;
         }
 

Project/Assets/ML-Agents/Examples/Soccer/Prefabs/SoccerFieldTwos.prefab

   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 030000000300000003000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &114492261207303438
 MonoBehaviour:
   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 030000000300000003000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &114850431417842684
 MonoBehaviour:
   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 030000000300000003000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &5320024511406682322
 MonoBehaviour:
   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 030000000300000003000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &5379409612883756837
 MonoBehaviour:

Project/Assets/ML-Agents/Examples/Soccer/Prefabs/StrikersVsGoalieField.prefab

   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 030000000300000003000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &114492261207303438
 MonoBehaviour:
   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 030000000300000003000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &114850431417842684
 MonoBehaviour:
   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 030000000300000003000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &5379409612883756837
 MonoBehaviour:

Project/Assets/ML-Agents/Examples/Tennis/Prefabs/TennisArea.prefab

   m_BrainParameters:
     VectorObservationSize: 9
     NumStackedVectorObservations: 3
+    m_ActionSpec:
+      m_NumContinuousActions: 3
+      BranchSizes: 
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114915946461826994
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1194790474478638
 GameObject:
   m_ObjectHideFlags: 0
   m_BrainParameters:
     VectorObservationSize: 9
     NumStackedVectorObservations: 3
+    m_ActionSpec:
+      m_NumContinuousActions: 3
+      BranchSizes: 
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
+  m_ObservableAttributeHandling: 0
 --- !u!114 &114800310164848628
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Script: {fileID: 11500000, guid: 3a6da8f78a394c6ab027688eab81e04d, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
+  debugCommandLineOverride: 
 --- !u!1 &1969551055586186
 GameObject:
   m_ObjectHideFlags: 0

Project/Assets/ML-Agents/Examples/Walker/Prefabs/Ragdoll/WalkerRagdollBase.prefab

   m_BrainParameters:
     VectorObservationSize: 243
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 39
+      BranchSizes: 
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &7408209125961349353
 MonoBehaviour:
     maxStep: 0
   hasUpgradedFromAgentParameters: 1
   MaxStep: 5000
-  targetWalkingSpeed: 10
+  m_TargetWalkingSpeed: 10
-  walkDirectionMethod: 0
-  worldDirToWalk: {x: 1, y: 0, z: 0}
-  worldPosToWalkTo: {x: 0, y: 0, z: 0}
   target: {fileID: 0}
   hips: {fileID: 895268871264836332}
   chest: {fileID: 7933235354845945071}

Project/Assets/ML-Agents/Examples/Walker/Prefabs/Ragdoll/WalkerRagdollDySingleSpeedVariant.prefab

       value: 
       objectReference: {fileID: 11400000, guid: 47e7c480450ec4dcd9e4a04124e14ed4,
         type: 3}
+    - target: {fileID: 895268871377934297, guid: 765582efd9dda46ed98564603316353f,
+        type: 3}
+      propertyPath: m_InferenceDevice
+      value: 2
+      objectReference: {fileID: 0}
     - target: {fileID: 895268871377934298, guid: 765582efd9dda46ed98564603316353f,
         type: 3}
       propertyPath: m_LocalPosition.x

Project/Assets/ML-Agents/Examples/WallJump/Prefabs/WallJumpArea.prefab

   m_BrainParameters:
     VectorObservationSize: 4
     NumStackedVectorObservations: 6
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 03000000030000000300000002000000
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
+  m_UseChildActuators: 1
   m_ObservableAttributeHandling: 0
 --- !u!114 &114925928594762506
 MonoBehaviour:

Project/Assets/ML-Agents/Examples/Worm/Prefabs/WormBasePrefab.prefab

   m_BrainParameters:
     VectorObservationSize: 64
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 9
+      BranchSizes: 
+    hasUpgradedBrainParametersWithActionSpec: 1
-  m_InferenceDevice: 0
+  m_InferenceDevice: 2
   m_BehaviorType: 0
   m_BehaviorName: WormDynamic
   TeamId: 0

com.unity.ml-agents/CHANGELOG.md

 and this project adheres to
 [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+### Major Changes
+#### com.unity.ml-agents (C#)
+#### ml-agents / ml-agents-envs / gym-unity (Python)
-## [Unreleased]
+### Minor Changes
+#### com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
+#### ml-agents / ml-agents-envs / gym-unity (Python)
+
+### Bug Fixes
+#### com.unity.ml-agents (C#)
+#### ml-agents / ml-agents-envs / gym-unity (Python)
+
+
+## [1.8.0-preview] - 2021-02-17
+- A plugin system for `mlagents-learn` has been added. You can now define custom
+  `StatsWriter` implementations and register them to be called during training.
+  More types of plugins will be added in the future. (#4788)
 
 ### Minor Changes
 #### com.unity.ml-agents / com.unity.ml-agents.extensions (C#)
 - The Barracuda dependency was upgraded to 1.3.0. (#4898)
 - Added `ActuatorComponent.CreateActuators`, and deprecate `ActuatorComponent.CreateActuator`.  The
   default implementation will wrap `ActuatorComponent.CreateActuator` in an array and return that. (#4899)
+- `InferenceDevice.Burst` was added, indicating that Agent's model will be run using Barracuda's Burst backend.
+  This is the default for new Agents, but existing ones that use `InferenceDevice.CPU` should update to
+  `InferenceDevice.Burst`. (#4925)
 
 #### ml-agents / ml-agents-envs / gym-unity (Python)
 - Tensorboard now logs the Environment Reward as both a scalar and a histogram. (#4878)
+- The `mlagents_env` API has changed, `BehaviorSpec` now has a `observation_specs` property containing a list of `ObservationSpec`. For more information on `ObservationSpec` see [here](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Python-API.md#behaviorspec). (#4763, #4825)
 
 ### Bug Fixes
 #### com.unity.ml-agents (C#)
 - Removed unnecessary memory allocations in `SideChannelManager.GetSideChannelMessage()` (#4886)
 - Removed several memory allocations that happened during inference. On a test scene, this
   reduced the amount of memory allocated by approximately 25%. (#4887)
+- Removed several memory allocations that happened during inference with discrete actions. (#4922)
+- Properly catch permission errors when writing timer files. (#4921)
+- Unexpected exceptions during training initialization and shutdown are now logged. If you see
+  "noisy" logs, please let us know! (#4930, #4935)
 
 #### ml-agents / ml-agents-envs / gym-unity (Python)
 - Fixed a bug that would cause an exception when `RunOptions` was deserialized via `pickle`. (#4842)
   while waiting for a connection, and raises a better error message if it crashes. (#4880)
 - Passing a `-logfile` option in the `--env-args` option to `mlagents-learn` is
   no longer overwritten. (#4880)
+- The `load_weights` function was being called unnecessarily often in the Ghost Trainer leading to training slowdowns. (#4934)
 
 
 ## [1.7.2-preview] - 2020-12-22

com.unity.ml-agents/Runtime/Academy.cs

             {
                 // We try to exchange the first message with Python. If this fails, it means
                 // no Python Process is ready to train the environment. In this case, the
-                //environment must use Inference.
+                // environment must use Inference.
+                bool initSuccessful = false;
+                var communicatorInitParams = new CommunicatorInitParameters
+                {
+                    unityCommunicationVersion = k_ApiVersion,
+                    unityPackageVersion = k_PackageVersion,
+                    name = "AcademySingleton",
+                    CSharpCapabilities = new UnityRLCapabilities()
+                };
+
-                    var unityRlInitParameters = Communicator.Initialize(
-                        new CommunicatorInitParameters
-                        {
-                            unityCommunicationVersion = k_ApiVersion,
-                            unityPackageVersion = k_PackageVersion,
-                            name = "AcademySingleton",
-                            CSharpCapabilities = new UnityRLCapabilities()
-                        });
-                    UnityEngine.Random.InitState(unityRlInitParameters.seed);
-                    // We might have inference-only Agents, so set the seed for them too.
-                    m_InferenceSeed = unityRlInitParameters.seed;
-                    TrainerCapabilities = unityRlInitParameters.TrainerCapabilities;
-                    TrainerCapabilities.WarnOnPythonMissingBaseRLCapabilities();
+                    initSuccessful = Communicator.Initialize(
+                        communicatorInitParams,
+                        out var unityRlInitParameters
+                    );
+                    if (initSuccessful)
+                    {
+                        UnityEngine.Random.InitState(unityRlInitParameters.seed);
+                        // We might have inference-only Agents, so set the seed for them too.
+                        m_InferenceSeed = unityRlInitParameters.seed;
+                        TrainerCapabilities = unityRlInitParameters.TrainerCapabilities;
+                        TrainerCapabilities.WarnOnPythonMissingBaseRLCapabilities();
+                    }
+                    else
+                    {
+                        Debug.Log($"Couldn't connect to trainer on port {port} using API version {k_ApiVersion}. Will perform inference instead.");
+                        Communicator = null;
+                    }
-                catch
+                catch (Exception ex)
-                    Debug.Log($"" +
-                        $"Couldn't connect to trainer on port {port} using API version {k_ApiVersion}. " +
-                        "Will perform inference instead."
-                    );
+                    Debug.Log($"Unexpected exception when trying to initialize communication: {ex}\nWill perform inference instead.");
+
             if (Communicator != null)
             {
                 Communicator.QuitCommandReceived += OnQuitCommandReceived;

com.unity.ml-agents/Runtime/Communicator/ICommunicator.cs

         /// Sends the academy parameters through the Communicator.
         /// Is used by the academy to send the AcademyParameters to the communicator.
         /// </summary>
-        /// <returns>The External Initialization Parameters received.</returns>
+        /// <returns>Whether the connection was successful.</returns>
-        UnityRLInitParameters Initialize(CommunicatorInitParameters initParameters);
+        /// <param name="initParametersOut">The External Initialization Parameters received</param>
+        bool Initialize(CommunicatorInitParameters initParameters, out UnityRLInitParameters initParametersOut);
 
         /// <summary>
         /// Registers a new Brain to the Communicator.

com.unity.ml-agents/Runtime/Communicator/RpcCommunicator.cs

 
         internal static bool CheckCommunicationVersionsAreCompatible(
             string unityCommunicationVersion,
-            string pythonApiVersion,
-            string pythonLibraryVersion)
+            string pythonApiVersion
+            )
         {
             var unityVersion = new Version(unityCommunicationVersion);
             var pythonVersion = new Version(pythonApiVersion);
         /// Sends the initialization parameters through the Communicator.
         /// Is used by the academy to send initialization parameters to the communicator.
         /// </summary>
-        /// <returns>The External Initialization Parameters received.</returns>
+        /// <returns>Whether the connection was successful.</returns>
-        public UnityRLInitParameters Initialize(CommunicatorInitParameters initParameters)
+        /// <param name="initParametersOut">The External Initialization Parameters received.</param>
+        public bool Initialize(CommunicatorInitParameters initParameters, out UnityRLInitParameters initParametersOut)
         {
             var academyParameters = new UnityRLInitializationOutputProto
             {
                     {
                         RlInitializationOutput = academyParameters
                     },