updated cube war

Project/Assets/ML-Agents/Examples/CubeWars/Prefabs/CubeWarArea.prefab

     VectorActionSize: 0300000003000000030000000200000002000000
     VectorActionDescriptions: []
     VectorActionSpaceType: 0
-  m_Model: {fileID: 11400000, guid: fa881d0c4f6b44ea9880a781d0771fc9, type: 3}
+  m_Model: {fileID: 11400000, guid: 73739d3fe797a457c972705ed75362f7, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
   m_BehaviorName: LargeCubeSoldier

Project/Assets/ML-Agents/Examples/CubeWars/Prefabs/SmallAgent.prefab

   m_PrefabInstance: {fileID: 0}
   m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 8083776131842293165}
-  m_LocalRotation: {x: -0, y: -0, z: -0, w: 1}
+  m_LocalRotation: {x: 0, y: 0, z: 0, w: 1}
   m_LocalPosition: {x: -24.8, y: 2, z: -9.559753}
   m_LocalScale: {x: 1, y: 1, z: 1}
   m_Children:
   m_Name: 
   m_EditorClassIdentifier: 
   m_BrainParameters:
-    VectorObservationSize: 4
+    VectorObservationSize: 14
-  m_Model: {fileID: 11400000, guid: 697e3166f993b4e4cb890de8be9ec842, type: 3}
+  m_Model: {fileID: 11400000, guid: 77d026617f8254b39b58e7f514762320, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
   m_BehaviorName: SmallCubeSoldier
   MaxStep: 0
   area: {fileID: 0}
   largeAgent: {fileID: 0}
+  HitPoints: 0
+  Teammate1: {fileID: 0}
+  Teammate2: {fileID: 0}
+  TeammateRb1: {fileID: 0}
+  TeammateRb2: {fileID: 0}
   turnSpeed: 300
   moveSpeed: 6
   normalMaterial: {fileID: 2100000, guid: c9fa44c2c3f8ce74ca39a3355ea42631, type: 2}
   m_Modification:
     m_TransformParent: {fileID: 8081094897351109481}
     m_Modifications:
-    - target: {fileID: 123071959092199671, guid: d40a32b30361e40b49d59bdfbbdb2e8c,
-        type: 3}
-      propertyPath: endPosition.x
-      value: 0
-      objectReference: {fileID: 0}
-    - target: {fileID: 123071959092199671, guid: d40a32b30361e40b49d59bdfbbdb2e8c,
-        type: 3}
-      propertyPath: endPosition.y
-      value: 10
-      objectReference: {fileID: 0}
-    - target: {fileID: 123071959092199671, guid: d40a32b30361e40b49d59bdfbbdb2e8c,
-        type: 3}
-      propertyPath: endPosition.z
-      value: 10
-      objectReference: {fileID: 0}
-    - target: {fileID: 123071959092199671, guid: d40a32b30361e40b49d59bdfbbdb2e8c,
-        type: 3}
-      propertyPath: width
-      value: 0.5
-      objectReference: {fileID: 0}
     - target: {fileID: 3343439013409978073, guid: d40a32b30361e40b49d59bdfbbdb2e8c,
         type: 3}
       propertyPath: m_LocalPosition.x
         type: 3}
       propertyPath: m_Name
       value: Laser
-      objectReference: {fileID: 0}
-    - target: {fileID: 9221550522079577563, guid: d40a32b30361e40b49d59bdfbbdb2e8c,
-        type: 3}
-      propertyPath: m_Positions.Array.data[1].z
-      value: 1
       objectReference: {fileID: 0}
     m_RemovedComponents: []
   m_SourcePrefab: {fileID: 100100000, guid: d40a32b30361e40b49d59bdfbbdb2e8c, type: 3}

Project/Assets/ML-Agents/Examples/CubeWars/Scripts/CubeWarArea.cs

         range = 1.0f;
         smallAgents = GetComponentsInChildren<SmallCubeAgent>();
         largeAgents = GetComponentsInChildren<LargeCubeAgent>();
+        smallAgents[0].Teammate1 = smallAgents[1];
+        smallAgents[0].Teammate2 = smallAgents[2];
+        smallAgents[0].TeammateRb1 = smallAgents[1].GetComponent<Rigidbody>();
+        smallAgents[0].TeammateRb2 = smallAgents[2].GetComponent<Rigidbody>();
+        smallAgents[1].Teammate1 = smallAgents[0];
+        smallAgents[1].Teammate2 = smallAgents[2];
+        smallAgents[1].TeammateRb1 = smallAgents[0].GetComponent<Rigidbody>();
+        smallAgents[1].TeammateRb2 = smallAgents[2].GetComponent<Rigidbody>();
+        smallAgents[2].Teammate1 = smallAgents[0];
+        smallAgents[2].Teammate2 = smallAgents[1];
+        smallAgents[2].TeammateRb1 = smallAgents[0].GetComponent<Rigidbody>();
+        smallAgents[2].TeammateRb2 = smallAgents[1].GetComponent<Rigidbody>();
+
     }
 
     public void AgentDied()

Project/Assets/ML-Agents/Examples/CubeWars/Scripts/SmallCubeAgent.cs

     bool m_Shoot;
     float m_ShootTime;
     Rigidbody m_AgentRb;
-    float m_HitPoints;
+    [HideInInspector]
+    public float HitPoints;
+    [HideInInspector]
+    public SmallCubeAgent Teammate1;
+    [HideInInspector]
+    public SmallCubeAgent Teammate2;
+    [HideInInspector]
+    public Rigidbody TeammateRb1;
+    [HideInInspector]
+    public Rigidbody TeammateRb2;
 
     // Speed of agent rotation.
     public float turnSpeed;
     public override void Initialize()
     {
         m_AgentRb = GetComponent<Rigidbody>();
-        //m_AgentRb.useGravity = true;
         m_MyArea = area.GetComponent<CubeWarArea>();
         m_LargeAgent = largeAgent.GetComponent<LargeCubeAgent>();
         m_CubeWarSettings = FindObjectOfType<CubeWarSettings>();
     {
         sensor.AddObservation(System.Convert.ToInt32(m_Shoot));
         sensor.AddObservation(System.Convert.ToInt32(m_Dead));
-        sensor.AddObservation(m_HitPoints);
+        sensor.AddObservation(HitPoints);
+
+        //Teammate 1 direction, normalized distance, hitpoints
+        Vector3 dirToT1 = Teammate1.transform.position - transform.position;
+        sensor.AddObservation(dirToT1.normalized);
+        sensor.AddObservation(Vector3.Distance(Teammate1.transform.position, transform.position) / 300f); //roughly normalized ditance
+        sensor.AddObservation(Teammate1.HitPoints);
+
+        Vector3 dirToT2 = Teammate2.transform.position - transform.position;
+        sensor.AddObservation(dirToT2.normalized);
+        sensor.AddObservation(Vector3.Distance(Teammate2.transform.position, transform.position) / 300f); //roughly normalized ditance
+        sensor.AddObservation(Teammate2.HitPoints);
+
         if (m_Dead)
         {
             AddReward(-.001f * m_Bonus);
             RaycastHit hit;
             if (Physics.SphereCast(transform.position, 2f, rayDir, out hit, 28f))
             {
-                if (hit.collider.gameObject.CompareTag("StrongSmallAgent") || hit.collider.gameObject.CompareTag("WeakSmallAgent"))
+                if (hit.collider.gameObject.CompareTag("StrongSmallAgent") || hit.collider.gameObject.CompareTag("WeakSmallAgent") || hit.collider.gameObject.CompareTag("DeadSmallAgent"))
                 {
                     hit.collider.gameObject.GetComponent<SmallCubeAgent>().HealAgent();
                 }
     {
         if (!m_Dead)
         {
-            m_HitPoints -= damage;
+            HitPoints -= damage;
             HealthStatus();
         }
     }
-        if (m_HitPoints < 1f)
+        if (HitPoints < 1f)
-            m_HitPoints = Mathf.Min(m_HitPoints + .25f, 1f);
+            HitPoints = Mathf.Min(HitPoints + .25f, 1f);
             HealthStatus();
         }
     }
-        if (m_HitPoints <= 1f && m_HitPoints > .5f)
+        if (HitPoints <= 1f && HitPoints > .5f)
         {
             m_Dead = false;
             gameObject.tag = "StrongSmallAgent";
-        else if (m_HitPoints <= .5f && m_HitPoints > 0.0f)
+        else if (HitPoints <= .5f && HitPoints > 0.0f)
         {
             m_Dead = false;
             gameObject.tag = "WeakSmallAgent";
 
     public override void OnEpisodeBegin()
     {
-        m_HitPoints = 1f;
+        HitPoints = 1f;
         HealthStatus();
         m_Dead = false;
         m_Shoot = false;

config/ppo/Tennis.yaml

         gamma: 0.99
     self_play:
       window: 10
-      play_against_latest_model_ratio: 0.5
-      save_steps: 50000
+      play_against_latest_model_ratio: 0.0
+      save_steps: 100000
-      team_change: 100000
+      team_change: 200000