Unity-Technologies · surfnerd · Jan 20, 2021 · Jan 12, 2021 · Jan 12, 2021 · Jan 12, 2021
diff --git a/.yamato/gym-interface-test.yml b/.yamato/gym-interface-test.yml
@@ -13,6 +13,7 @@ test_gym_interface_{{ editor.version }}:
     - |
       sudo apt-get update && sudo apt-get install -y python3-venv
       python3 -m venv venv && source venv/bin/activate
+      python -m pip install wheel --index-url https://artifactory.prd.it.unity3d.com/artifactory/api/pypi/pypi/simple
       python -m pip install pyyaml --index-url https://artifactory.prd.it.unity3d.com/artifactory/api/pypi/pypi/simple
       python -u -m ml-agents.tests.yamato.setup_venv
       python ml-agents/tests/yamato/scripts/run_gym.py --env=artifacts/testPlayer-Basic

diff --git a/Project/Assets/ML-Agents/Examples/Basic/Scripts/BasicActuatorComponent.cs b/Project/Assets/ML-Agents/Examples/Basic/Scripts/BasicActuatorComponent.cs
@@ -1,5 +1,6 @@
 using System;
 using Unity.MLAgents.Actuators;
+using UnityEngine;
 
 namespace Unity.MLAgentsExamples
 {
@@ -30,7 +31,7 @@ public override ActionSpec ActionSpec
     /// <summary>
     /// Simple actuator that converts the action into a {-1, 0, 1} direction
     /// </summary>
-    public class BasicActuator : IActuator
+    public class BasicActuator : IActuator, IHeuristicProvider
     {
         public BasicController basicController;
         ActionSpec m_ActionSpec;
@@ -76,6 +77,19 @@ public void OnActionReceived(ActionBuffers actionBuffers)
             basicController.MoveDirection(direction);
         }
 
+        public void Heuristic(in ActionBuffers actionBuffersOut)
+        {
+            var direction = Input.GetAxis("Horizontal");
+            var discreteActions = actionBuffersOut.DiscreteActions;
+            if (Mathf.Approximately(direction, 0.0f))
+            {
+                discreteActions[0] = 0;
+                return;
+            }
+            var sign = Math.Sign(direction);
+            discreteActions[0] = sign < 0 ? 1 : 2;
+        }
+
         public void WriteDiscreteActionMask(IDiscreteActionMask actionMask)
         {
 

diff --git a/Project/Assets/ML-Agents/Examples/Match3/Prefabs/Match3Heuristic.prefab b/Project/Assets/ML-Agents/Examples/Match3/Prefabs/Match3Heuristic.prefab
@@ -13,8 +13,8 @@ GameObject:
   - component: {fileID: 3508723250470608012}
   - component: {fileID: 3508723250470608011}
   - component: {fileID: 3508723250470608009}
-  - component: {fileID: 3508723250470608013}
   - component: {fileID: 3508723250470608014}
+  - component: {fileID: 2112317463290853299}
   m_Layer: 0
   m_Name: Match3 Agent
   m_TagString: Untagged
@@ -51,9 +51,13 @@ MonoBehaviour:
   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 
     VectorActionSize: 
     VectorActionDescriptions: []
     VectorActionSpaceType: 0
+    hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: c34da50737a3c4a50918002b20b2b927, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
@@ -81,7 +85,6 @@ MonoBehaviour:
   Board: {fileID: 0}
   MoveTime: 0.25
   MaxMoves: 500
-  HeuristicQuality: 0
 --- !u!114 &3508723250470608011
 MonoBehaviour:
   m_ObjectHideFlags: 0
@@ -96,7 +99,6 @@ MonoBehaviour:
   m_EditorClassIdentifier: 
   DebugMoveIndex: -1
   CubeSpacing: 1.25
-  Board: {fileID: 0}
   TilePrefab: {fileID: 4007900521885639951, guid: faee4e805953b49e688bd00b45c55f2e,
     type: 3}
 --- !u!114 &3508723250470608009
@@ -119,7 +121,7 @@ MonoBehaviour:
   BasicCellPoints: 1
   SpecialCell1Points: 2
   SpecialCell2Points: 3
---- !u!114 &3508723250470608013
+--- !u!114 &3508723250470608014
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_CorrespondingSourceObject: {fileID: 0}
@@ -128,12 +130,12 @@ MonoBehaviour:
   m_GameObject: {fileID: 3508723250470608007}
   m_Enabled: 1
   m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 08e4b0da54cb4d56bfcbae22dd49ab8d, type: 3}
+  m_Script: {fileID: 11500000, guid: 530d2f105aa145bd8a00e021bdd925fd, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  ActuatorName: Match3 Actuator
-  ForceHeuristic: 1
---- !u!114 &3508723250470608014
+  SensorName: Match3 Sensor
+  ObservationType: 0
+--- !u!114 &2112317463290853299
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_CorrespondingSourceObject: {fileID: 0}
@@ -142,11 +144,12 @@ MonoBehaviour:
   m_GameObject: {fileID: 3508723250470608007}
   m_Enabled: 1
   m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 530d2f105aa145bd8a00e021bdd925fd, type: 3}
+  m_Script: {fileID: 11500000, guid: b17adcc6c9b241da903aa134f2dac930, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  SensorName: Match3 Sensor
-  ObservationType: 0
+  ActuatorName: Match3 Actuator
+  ForceHeuristic: 1
+  HeuristicQuality: 0
 --- !u!1 &3508723250774301855
 GameObject:
   m_ObjectHideFlags: 0

diff --git a/Project/Assets/ML-Agents/Examples/Match3/Prefabs/Match3VectorObs.prefab b/Project/Assets/ML-Agents/Examples/Match3/Prefabs/Match3VectorObs.prefab
@@ -44,8 +44,8 @@ GameObject:
   - component: {fileID: 2118285884327540682}
   - component: {fileID: 2118285884327540685}
   - component: {fileID: 2118285884327540687}
-  - component: {fileID: 2118285884327540683}
   - component: {fileID: 2118285884327540680}
+  - component: {fileID: 3357012711826686276}
   m_Layer: 0
   m_Name: Match3 Agent
   m_TagString: Untagged
@@ -82,9 +82,13 @@ MonoBehaviour:
   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 
     VectorActionSize: 
     VectorActionDescriptions: []
     VectorActionSpaceType: 0
+    hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 9e89b8e81974148d3b7213530d00589d, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
@@ -112,7 +116,6 @@ MonoBehaviour:
   Board: {fileID: 0}
   MoveTime: 0.25
   MaxMoves: 500
-  HeuristicQuality: 0
 --- !u!114 &2118285884327540685
 MonoBehaviour:
   m_ObjectHideFlags: 0
@@ -127,7 +130,6 @@ MonoBehaviour:
   m_EditorClassIdentifier: 
   DebugMoveIndex: -1
   CubeSpacing: 1.25
-  Board: {fileID: 0}
   TilePrefab: {fileID: 4007900521885639951, guid: faee4e805953b49e688bd00b45c55f2e,
     type: 3}
 --- !u!114 &2118285884327540687
@@ -150,7 +152,7 @@ MonoBehaviour:
   BasicCellPoints: 1
   SpecialCell1Points: 2
   SpecialCell2Points: 3
---- !u!114 &2118285884327540683
+--- !u!114 &2118285884327540680
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_CorrespondingSourceObject: {fileID: 0}
@@ -159,12 +161,12 @@ MonoBehaviour:
   m_GameObject: {fileID: 2118285884327540673}
   m_Enabled: 1
   m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 08e4b0da54cb4d56bfcbae22dd49ab8d, type: 3}
+  m_Script: {fileID: 11500000, guid: 530d2f105aa145bd8a00e021bdd925fd, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  ActuatorName: Match3 Actuator
-  ForceHeuristic: 0
---- !u!114 &2118285884327540680
+  SensorName: Match3 Sensor
+  ObservationType: 0
+--- !u!114 &3357012711826686276
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_CorrespondingSourceObject: {fileID: 0}
@@ -173,8 +175,9 @@ MonoBehaviour:
   m_GameObject: {fileID: 2118285884327540673}
   m_Enabled: 1
   m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 530d2f105aa145bd8a00e021bdd925fd, type: 3}
+  m_Script: {fileID: 11500000, guid: b17adcc6c9b241da903aa134f2dac930, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  SensorName: Match3 Sensor
-  ObservationType: 0
+  ActuatorName: Match3 Actuator
+  ForceHeuristic: 0
+  HeuristicQuality: 0
diff --git a/Project/Assets/ML-Agents/Examples/Match3/Prefabs/Match3VisualObs.prefab b/Project/Assets/ML-Agents/Examples/Match3/Prefabs/Match3VisualObs.prefab
@@ -44,8 +44,8 @@ GameObject:
   - component: {fileID: 3019509692332007781}
   - component: {fileID: 3019509692332007778}
   - component: {fileID: 3019509692332007776}
-  - component: {fileID: 3019509692332007780}
   - component: {fileID: 3019509692332007783}
+  - component: {fileID: 8270768986451624427}
   m_Layer: 0
   m_Name: Match3 Agent
   m_TagString: Untagged
@@ -82,9 +82,13 @@ MonoBehaviour:
   m_BrainParameters:
     VectorObservationSize: 0
     NumStackedVectorObservations: 1
+    m_ActionSpec:
+      m_NumContinuousActions: 0
+      BranchSizes: 
     VectorActionSize: 
     VectorActionDescriptions: []
     VectorActionSpaceType: 0
+    hasUpgradedBrainParametersWithActionSpec: 1
   m_Model: {fileID: 11400000, guid: 48d14da88fea74d0693c691c6e3f2e34, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
@@ -112,7 +116,6 @@ MonoBehaviour:
   Board: {fileID: 0}
   MoveTime: 0.25
   MaxMoves: 500
-  HeuristicQuality: 0
 --- !u!114 &3019509692332007778
 MonoBehaviour:
   m_ObjectHideFlags: 0
@@ -127,7 +130,6 @@ MonoBehaviour:
   m_EditorClassIdentifier: 
   DebugMoveIndex: -1
   CubeSpacing: 1.25
-  Board: {fileID: 0}
   TilePrefab: {fileID: 4007900521885639951, guid: faee4e805953b49e688bd00b45c55f2e,
     type: 3}
 --- !u!114 &3019509692332007776
@@ -150,7 +152,7 @@ MonoBehaviour:
   BasicCellPoints: 1
   SpecialCell1Points: 2
   SpecialCell2Points: 3
---- !u!114 &3019509692332007780
+--- !u!114 &3019509692332007783
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_CorrespondingSourceObject: {fileID: 0}
@@ -159,12 +161,12 @@ MonoBehaviour:
   m_GameObject: {fileID: 3019509692332007790}
   m_Enabled: 1
   m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 08e4b0da54cb4d56bfcbae22dd49ab8d, type: 3}
+  m_Script: {fileID: 11500000, guid: 530d2f105aa145bd8a00e021bdd925fd, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  ActuatorName: Match3 Actuator
-  ForceHeuristic: 0
---- !u!114 &3019509692332007783
+  SensorName: Match3 Sensor
+  ObservationType: 2
+--- !u!114 &8270768986451624427
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_CorrespondingSourceObject: {fileID: 0}
@@ -173,8 +175,9 @@ MonoBehaviour:
   m_GameObject: {fileID: 3019509692332007790}
   m_Enabled: 1
   m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 530d2f105aa145bd8a00e021bdd925fd, type: 3}
+  m_Script: {fileID: 11500000, guid: b17adcc6c9b241da903aa134f2dac930, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  SensorName: Match3 Sensor
-  ObservationType: 2
+  ActuatorName: Match3 Actuator
+  ForceHeuristic: 0
+  HeuristicQuality: 0
diff --git a/Project/Assets/ML-Agents/Examples/Match3/Scenes/Match3.unity b/Project/Assets/ML-Agents/Examples/Match3/Scenes/Match3.unity
@@ -690,6 +690,11 @@ PrefabInstance:
   m_Modification:
     m_TransformParent: {fileID: 0}
     m_Modifications:
+    - target: {fileID: 2112317463290853299, guid: 2fafdcd0587684641b03b11f04454f1b,
+        type: 3}
+      propertyPath: HeuristicQuality
+      value: 1
+      objectReference: {fileID: 0}
     - target: {fileID: 3508723250470608011, guid: 2fafdcd0587684641b03b11f04454f1b,
         type: 3}
       propertyPath: cubeSpacing
@@ -1385,6 +1390,11 @@ PrefabInstance:
   m_Modification:
     m_TransformParent: {fileID: 0}
     m_Modifications:
+    - target: {fileID: 2112317463290853299, guid: 2fafdcd0587684641b03b11f04454f1b,
+        type: 3}
+      propertyPath: HeuristicQuality
+      value: 1
+      objectReference: {fileID: 0}
     - target: {fileID: 3508723250470608011, guid: 2fafdcd0587684641b03b11f04454f1b,
         type: 3}
       propertyPath: cubeSpacing