refactor collab agent

Project/Assets/ML-Agents/Examples/Soccer/Scenes/SoccerTwos.unity

     m_EnableBakedLightmaps: 1
     m_EnableRealtimeLightmaps: 1
   m_LightmapEditorSettings:
-    serializedVersion: 10
+    serializedVersion: 12
     m_Resolution: 2
     m_BakeResolution: 40
     m_AtlasSize: 1024
     m_CompAOExponentDirect: 0
+    m_ExtractAmbientOcclusion: 0
     m_Padding: 2
     m_LightmapParameters: {fileID: 0}
     m_LightmapsBakeMode: 1
     m_PVRDirectSampleCount: 32
     m_PVRSampleCount: 500
     m_PVRBounces: 2
+    m_PVREnvironmentSampleCount: 500
+    m_PVREnvironmentReferencePointCount: 2048
+    m_PVRFilteringMode: 2
+    m_PVRDenoiserTypeDirect: 0
+    m_PVRDenoiserTypeIndirect: 0
+    m_PVRDenoiserTypeAO: 0
-    m_PVRFilteringMode: 1
+    m_PVREnvironmentMIS: 0
     m_PVRCulling: 1
     m_PVRFilteringGaussRadiusDirect: 1
     m_PVRFilteringGaussRadiusIndirect: 5
     m_PVRFilteringAtrousPositionSigmaAO: 1
-    m_ShowResolutionOverlay: 1
+    m_ExportTrainingData: 0
+    m_TrainingDataDestination: TrainingData
   m_LightingDataAsset: {fileID: 112000002, guid: 03723c7f910c3423aa1974f1b9ce8392,
     type: 2}
   m_UseShadowmask: 1
   m_GameObject: {fileID: 255077123}
   m_Enabled: 1
   m_EditorHideFlags: 0
-  m_Script: {fileID: 1077351063, guid: f70555f144d8491a825f0804e09c671c, type: 3}
+  m_Script: {fileID: 11500000, guid: 4f231c4fb786f3946a6b90b886c48677, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
   m_HorizontalAxis: Horizontal
   m_GameObject: {fileID: 255077123}
   m_Enabled: 1
   m_EditorHideFlags: 0
-  m_Script: {fileID: -619905303, guid: f70555f144d8491a825f0804e09c671c, type: 3}
+  m_Script: {fileID: 11500000, guid: 76c392e42b5098c458856cdf6ecaaaa1, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
   m_FirstSelected: {fileID: 0}
   m_Modification:
     m_TransformParent: {fileID: 0}
     m_Modifications:
+    - target: {fileID: 1537641056927260, guid: 3ce107b4a79bc4eef83afde434932a68, type: 3}
+      propertyPath: m_IsActive
+      value: 0
+      objectReference: {fileID: 0}
     - target: {fileID: 224194346362733190, guid: 3ce107b4a79bc4eef83afde434932a68,
         type: 3}
       propertyPath: m_LocalPosition.x
       objectReference: {fileID: 0}
     - target: {fileID: 1141134673700168, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_IsActive
-      value: 1
+      value: 0
       objectReference: {fileID: 0}
     - target: {fileID: 4558743310993102, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_LocalPosition.x
       propertyPath: m_RootOrder
       value: 4
       objectReference: {fileID: 0}
+    - target: {fileID: 4540201673231058, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
+      propertyPath: m_LocalPosition.x
+      value: 0
+      objectReference: {fileID: 0}
     m_RemovedComponents: []
   m_SourcePrefab: {fileID: 100100000, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
 --- !u!1 &1009000883
   m_ClearFlags: 2
   m_BackGroundColor: {r: 0.46666667, g: 0.5647059, b: 0.60784316, a: 1}
   m_projectionMatrixMode: 1
+  m_GateFitMode: 2
+  m_FOVAxisMode: 0
-  m_GateFitMode: 2
   m_FocalLength: 50
   m_NormalizedViewPortRect:
     serializedVersion: 2
       objectReference: {fileID: 0}
     - target: {fileID: 1141134673700168, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_IsActive
-      value: 1
+      value: 0
       objectReference: {fileID: 0}
     - target: {fileID: 4558743310993102, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_LocalPosition.x
       objectReference: {fileID: 0}
     - target: {fileID: 1141134673700168, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_IsActive
-      value: 1
+      value: 0
       objectReference: {fileID: 0}
     - target: {fileID: 4558743310993102, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_LocalPosition.x
       objectReference: {fileID: 0}
     - target: {fileID: 1141134673700168, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_IsActive
-      value: 1
+      value: 0
       objectReference: {fileID: 0}
     - target: {fileID: 4558743310993102, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_LocalPosition.x
   m_Name: 
   m_EditorClassIdentifier: 
   gravityMultiplier: 1
-  monitorVerticalOffset: 0
+  reuseCollisionCallbacks: 1
 --- !u!114 &1574236051
 MonoBehaviour:
   m_ObjectHideFlags: 0
   blueMaterial: {fileID: 2100000, guid: c9fa44c2c3f8ce74ca39a3355ea42631, type: 2}
   randomizePlayersTeamForTraining: 0
   agentRunSpeed: 2
-  strikerPunish: -0.1
-  strikerReward: 1
-  goaliePunish: -1
-  goalieReward: 0.1
 --- !u!1001 &1606160104
 PrefabInstance:
   m_ObjectHideFlags: 0
       objectReference: {fileID: 0}
     - target: {fileID: 1141134673700168, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_IsActive
-      value: 1
+      value: 0
       objectReference: {fileID: 0}
     - target: {fileID: 4558743310993102, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_LocalPosition.x
       objectReference: {fileID: 0}
     - target: {fileID: 1141134673700168, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_IsActive
-      value: 1
+      value: 0
       objectReference: {fileID: 0}
     - target: {fileID: 4558743310993102, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_LocalPosition.x
       objectReference: {fileID: 0}
     - target: {fileID: 1141134673700168, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_IsActive
-      value: 1
+      value: 0
       objectReference: {fileID: 0}
     - target: {fileID: 4558743310993102, guid: 54f3340298537426e96a6cc530e2d5d8, type: 3}
       propertyPath: m_LocalPosition.x

Project/Assets/ML-Agents/Examples/Soccer/Scripts/AgentSoccer.cs

     public Team team;
     float m_KickPower;
     int m_PlayerIndex;
-    int m_Previous = 0;
     public SoccerFieldArea area;
 
     // The coefficient for the reward for colliding with a ball. Set using curriculum.
     float m_Existential;
     float m_LateralSpeed;
     float m_ForwardSpeed;
-    float[] m_Message = new float[10];
-    public GameObject teammate_gb;
-    AgentSoccer teammate;
 
     [HideInInspector]
     public float timePenalty;
     {
         m_Existential = 1f / MaxStep;
         m_BehaviorParameters = gameObject.GetComponent<BehaviorParameters>();
-        teammate = teammate_gb.GetComponent<AgentSoccer>();
         if (m_BehaviorParameters.TeamId == (int)Team.Blue)
         {
             team = Team.Blue;
             timePenalty -= m_Existential;
         }
         MoveAgent(actionBuffers.DiscreteActions);
-        teammate.tellAgent(actionBuffers.DiscreteActions[3]);
-    public override void CollectObservations(VectorSensor sensor)
-    {
-
-        sensor.AddObservation(m_Message);
-    }
-
-    public void tellAgent(int message)
-    {
-        m_Message[m_Previous] = 0f;
-        m_Message[message] = 1f;
-        m_Previous = message;
-    }
 
     public override void Heuristic(in ActionBuffers actionsOut)
     {
         agentRb.velocity = Vector3.zero;
         agentRb.angularVelocity = Vector3.zero;
         SetResetParameters();
-        System.Array.Clear(m_Message, 0, m_Message.Length);
     }
 
     public void SetResetParameters()

Project/Assets/ML-Agents/Examples/Soccer/Scripts/AgentSoccerCollab.cs

+using UnityEngine;
+using Unity.MLAgents;
+using Unity.MLAgents.Actuators;
+using Unity.MLAgents.Policies;
+using Unity.MLAgents.Sensors;
+
+public class AgentSoccerCollab : AgentSoccer
+{
+    public int tester = 0;
+    int m_Previous = 0;
+
+
+    float[] m_Message = new float[10];
+    public GameObject teammate_gb;
+    AgentSoccerCollab teammate;
+
+    public override void Initialize()
+    {
+        base.Initialize();
+        teammate = teammate_gb.GetComponent<AgentSoccerCollab>();
+    }
+
+    public override void OnActionReceived(ActionBuffers actionBuffers)
+
+    {
+        base.OnActionReceived(actionBuffers);
+        //if (team == Team.Blue && tester == 1)
+        //{
+        //    Debug.Log(actionBuffers.DiscreteActions[3]);
+        //}
+        teammate.tellAgent(actionBuffers.DiscreteActions[3]);
+    }
+
+    public override void CollectObservations(VectorSensor sensor)
+    {
+
+        sensor.AddObservation(m_Message);
+    }
+
+    public void tellAgent(int message)
+    {
+        m_Message[m_Previous] = 0f;
+        m_Message[message] = 1f;
+        m_Previous = message;
+    }
+
+    public override void OnEpisodeBegin()
+    {
+        base.OnEpisodeBegin();
+        System.Array.Clear(m_Message, 0, m_Message.Length);
+    }
+
+    public override void Heuristic(in ActionBuffers actionsOut)
+    {
+        var discreteActionsOut = actionsOut.DiscreteActions;
+        discreteActionsOut.Clear();
+        if (Input.GetKey(KeyCode.Alpha0))
+        {
+            discreteActionsOut[3] = 0;
+        }
+        if (Input.GetKey(KeyCode.Alpha1))
+        {
+            discreteActionsOut[3] = 1;
+        }
+        if (Input.GetKey(KeyCode.Alpha2))
+        {
+            discreteActionsOut[3] = 2;
+        }
+        if (Input.GetKey(KeyCode.Alpha3))
+        {
+            discreteActionsOut[3] = 3;
+        }
+        if (Input.GetKey(KeyCode.Alpha4))
+        {
+            discreteActionsOut[3] = 4;
+        }
+        if (Input.GetKey(KeyCode.Alpha5))
+        {
+            discreteActionsOut[3] = 5;
+        }
+        if (Input.GetKey(KeyCode.Alpha6))
+        {
+            discreteActionsOut[3] = 6;
+        }
+        if (Input.GetKey(KeyCode.Alpha7))
+        {
+            discreteActionsOut[3] = 7;
+        }
+        if (Input.GetKey(KeyCode.Alpha8))
+        {
+            discreteActionsOut[3] = 8;
+        }
+        if (Input.GetKey(KeyCode.Alpha9))
+        {
+            discreteActionsOut[3] = 9;
+        }
+        //forward
+        if (Input.GetKey(KeyCode.W))
+        {
+            discreteActionsOut[0] = 1;
+        }
+        if (Input.GetKey(KeyCode.S))
+        {
+            discreteActionsOut[0] = 2;
+        }
+        //rotate
+        if (Input.GetKey(KeyCode.A))
+        {
+            discreteActionsOut[2] = 1;
+        }
+        if (Input.GetKey(KeyCode.D))
+        {
+            discreteActionsOut[2] = 2;
+        }
+        //right
+        if (Input.GetKey(KeyCode.E))
+        {
+            discreteActionsOut[1] = 1;
+        }
+        if (Input.GetKey(KeyCode.Q))
+        {
+            discreteActionsOut[1] = 2;
+        }
+    }
+}

Project/Assets/ML-Agents/Examples/Soccer/Scripts/AgentSoccerCollab.cs.meta

+fileFormatVersion: 2
+guid: 506fb6eabb24441ffa15342d72f0bdd2
+MonoImporter:
+  externalObjects: {}
+  serializedVersion: 2
+  defaultReferences: []
+  executionOrder: 0
+  icon: {instanceID: 0}
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: 

Project/Assets/ML-Agents/Examples/Soccer/TFModels/SoccerTwos-10999921.onnx.meta

+fileFormatVersion: 2
+guid: fb0dcbf8aad8340428473b83fbb41557
+ScriptedImporter:
+  internalIDToNameTable: []
+  externalObjects: {}
+  serializedVersion: 2
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: 
+  script: {fileID: 11500000, guid: 683b6cb6d0a474744822c888b46772c9, type: 3}
+  optimizeModel: 1
+  forceArbitraryBatchSize: 1
+  treatErrorsAsWarnings: 0