new reacher reward

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

     VectorActionSize: 04000000
     VectorActionDescriptions: []
     VectorActionSpaceType: 1
-  m_Model: {fileID: 11400000, guid: d7bdb6a78154f4cf99437d67e4a569a8, type: 3}
+  m_Model: {fileID: 11400000, guid: e12acd64209f9468c899b9708b2702c3, type: 3}
   m_InferenceDevice: 0
   m_BehaviorType: 0
   m_BehaviorName: Reacher

Project/Assets/ML-Agents/Examples/Reacher/Scripts/NewReacherGoal.cs

     {
         if (other.gameObject == hand)
         {
-            agent.GetComponent<NewReacherAgent>().AddReward(0.01f);
+            agent.GetComponent<NewReacherAgent>().AddReward(0.05f);
         }
     }
 }

Project/Assets/ML-Agents/Examples/Reacher/Scripts/ReacherAgent.cs

         var torqueZ = Mathf.Clamp(vectorAction[1], -1f, 1f) * 150f;
         m_RbA.AddTorque(new Vector3(torqueX, 0f, torqueZ));
 
-        
-
-                        + vectorAction[1] * vectorAction[1] 
-                        + vectorAction[2] * vectorAction[2] 
-                        + vectorAction[3] * vectorAction[3] 
-                ));
+                + vectorAction[1] * vectorAction[1] 
+                + vectorAction[2] * vectorAction[2] 
+                + vectorAction[3] * vectorAction[3] 
+        ));
     }
 
     /// <summary>
     {
+        AddReward( - 0.001f * (goal.transform.position - hand.transform.position).magnitude);
+        // Debug.Log( - 0.001f * (goal.transform.position - hand.transform.position).magnitude);
         var radians = m_GoalDegree * Mathf.PI / 180f;
         var goalX = 8f * Mathf.Cos(radians);
         var goalY = 8f * Mathf.Sin(radians);

Project/Assets/ML-Agents/Examples/Reacher/Scripts/ReacherGoal.cs

     {
         if (other.gameObject == hand)
         {
-            agent.GetComponent<ReacherAgent>().AddReward(0.01f);
+            agent.GetComponent<ReacherAgent>().AddReward(0.05f);
         }
     }
 }

config/sac/Reacher.yaml

         gamma: 0.99
         strength: 1.0
     keep_checkpoints: 5
-    max_steps: 6000000
+    max_steps: 3000000
     time_horizon: 1000
     summary_freq: 60000
     threaded: true

config/sac_transfer/Reacher.yaml

         gamma: 0.99
         strength: 1.0
     keep_checkpoints: 5
-    max_steps: 6000000
+    max_steps: 3000000
     time_horizon: 1000
     summary_freq: 60000
     threaded: true

config/sac_transfer/ReacherTransfer.yaml

       train_model: false
       load_action: true
       train_action: false
-      transfer_path: "results/sacmod_reacher-qr/Reacher"
+      transfer_path: "results/reacher/Reacher"
     network_settings:
       normalize: true
       hidden_units: 128
         gamma: 0.99
         strength: 1.0
     keep_checkpoints: 5
-    max_steps: 6000000
+    max_steps: 3000000
     time_horizon: 1000
     summary_freq: 60000
     threaded: true