Renaming Agent's methods

Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DAgent.cs

@@ -10,7 +10,7 @@ public class Ball3DAgent : Agent
     Rigidbody m_BallRb;
     FloatPropertiesChannel m_ResetParams;
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_BallRb = ball.GetComponent<Rigidbody>();
         m_ResetParams = Academy.Instance.FloatProperties;
@@ -25,7 +25,7 @@ public override void CollectObservations(VectorSensor sensor)
         sensor.AddObservation(m_BallRb.velocity);
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         var actionZ = 2f * Mathf.Clamp(vectorAction[0], -1f, 1f);
         var actionX = 2f * Mathf.Clamp(vectorAction[1], -1f, 1f);
@@ -46,15 +46,15 @@ public override void AgentAction(float[] vectorAction)
             Mathf.Abs(ball.transform.position.z - gameObject.transform.position.z) > 3f)
         {
             SetReward(-1f);
-            Done();
+            EndEpisode();
         }
         else
         {
             SetReward(0.1f);
         }
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         gameObject.transform.rotation = new Quaternion(0f, 0f, 0f, 0f);
         gameObject.transform.Rotate(new Vector3(1, 0, 0), Random.Range(-10f, 10f));

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

@@ -10,7 +10,7 @@ public class Ball3DHardAgent : Agent
     Rigidbody m_BallRb;
     FloatPropertiesChannel m_ResetParams;
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_BallRb = ball.GetComponent<Rigidbody>();
         m_ResetParams = Academy.Instance.FloatProperties;
@@ -24,7 +24,7 @@ public override void CollectObservations(VectorSensor sensor)
         sensor.AddObservation((ball.transform.position - gameObject.transform.position));
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         var actionZ = 2f * Mathf.Clamp(vectorAction[0], -1f, 1f);
         var actionX = 2f * Mathf.Clamp(vectorAction[1], -1f, 1f);
@@ -45,15 +45,15 @@ public override void AgentAction(float[] vectorAction)
             Mathf.Abs(ball.transform.position.z - gameObject.transform.position.z) > 3f)
         {
             SetReward(-1f);
-            Done();
+            EndEpisode();
         }
         else
         {
             SetReward(0.1f);
         }
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         gameObject.transform.rotation = new Quaternion(0f, 0f, 0f, 0f);
         gameObject.transform.Rotate(new Vector3(1, 0, 0), Random.Range(-10f, 10f));

Project/Assets/ML-Agents/Examples/Basic/Scripts/BasicController.cs

@@ -59,14 +59,14 @@ public void ApplyAction(float[] vectorAction)
         if (m_Position == k_SmallGoalPosition)
         {
             m_Agent.AddReward(0.1f);
-            m_Agent.Done();
+            m_Agent.EndEpisode();
             ResetAgent();
         }
 
         if (m_Position == k_LargeGoalPosition)
         {
             m_Agent.AddReward(1f);
-            m_Agent.Done();
+            m_Agent.EndEpisode();
             ResetAgent();
         }
     }

Project/Assets/ML-Agents/Examples/Bouncer/Scripts/BouncerAgent.cs

@@ -17,7 +17,7 @@ public class BouncerAgent : Agent
 
     FloatPropertiesChannel m_ResetParams;
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_Rb = gameObject.GetComponent<Rigidbody>();
         m_LookDir = Vector3.zero;
@@ -33,7 +33,7 @@ public override void CollectObservations(VectorSensor sensor)
         sensor.AddObservation(target.transform.localPosition);
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         for (var i = 0; i < vectorAction.Length; i++)
         {
@@ -52,7 +52,7 @@ public override void AgentAction(float[] vectorAction)
         m_LookDir = new Vector3(x, y, z);
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         gameObject.transform.localPosition = new Vector3(
             (1 - 2 * Random.value) * 5, 2, (1 - 2 * Random.value) * 5);
@@ -85,20 +85,20 @@ void FixedUpdate()
         if (gameObject.transform.position.y < -1)
         {
             AddReward(-1);
-            Done();
+            EndEpisode();
             return;
         }
 
         if (gameObject.transform.localPosition.x < -19 || gameObject.transform.localPosition.x > 19
             || gameObject.transform.localPosition.z < -19 || gameObject.transform.localPosition.z > 19)
         {
             AddReward(-1);
-            Done();
+            EndEpisode();
             return;
         }
         if (m_JumpLeft == 0)
         {
-            Done();
+            EndEpisode();
         }
     }
 

Project/Assets/ML-Agents/Examples/Crawler/Scripts/CrawlerAgent.cs

@@ -52,7 +52,7 @@ public class CrawlerAgent : Agent
     Quaternion m_LookRotation;
     Matrix4x4 m_TargetDirMatrix;
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_JdController = GetComponent<JointDriveController>();
         m_DirToTarget = target.position - body.position;
@@ -147,7 +147,7 @@ public void GetRandomTargetPos()
         target.position = newTargetPos + ground.position;
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         // The dictionary with all the body parts in it are in the jdController
         var bpDict = m_JdController.bodyPartsDict;
@@ -251,7 +251,7 @@ void RewardFunctionTimePenalty()
     /// <summary>
     /// Loop over body parts and reset them to initial conditions.
     /// </summary>
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         if (m_DirToTarget != Vector3.zero)
         {

Project/Assets/ML-Agents/Examples/FoodCollector/Scripts/FoodCollectorAgent.cs

@@ -29,9 +29,8 @@ public class FoodCollectorAgent : Agent
     public bool useVectorObs;
 
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
-        base.InitializeAgent();
         m_AgentRb = GetComponent<Rigidbody>();
         m_MyArea = area.GetComponent<FoodCollectorArea>();
         m_FoodCollecterSettings = FindObjectOfType<FoodCollectorSettings>();
@@ -202,7 +201,7 @@ void Unsatiate()
         gameObject.GetComponentInChildren<Renderer>().material = normalMaterial;
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         MoveAgent(vectorAction);
     }
@@ -230,7 +229,7 @@ public override float[] Heuristic()
         return action;
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         Unfreeze();
         Unpoison();

Project/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAgent.cs

@@ -28,10 +28,6 @@ public class GridAgent : Agent
     const int k_Left = 3;
     const int k_Right = 4;
 
-    public override void InitializeAgent()
-    {
-    }
-
     public override void CollectDiscreteActionMasks(DiscreteActionMasker actionMasker)
     {
         // Mask the necessary actions if selected by the user.
@@ -65,7 +61,7 @@ public override void CollectDiscreteActionMasks(DiscreteActionMasker actionMaske
     }
 
     // to be implemented by the developer
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         AddReward(-0.01f);
         var action = Mathf.FloorToInt(vectorAction[0]);
@@ -101,12 +97,12 @@ public override void AgentAction(float[] vectorAction)
             if (hit.Where(col => col.gameObject.CompareTag("goal")).ToArray().Length == 1)
             {
                 SetReward(1f);
-                Done();
+                EndEpisode();
             }
             else if (hit.Where(col => col.gameObject.CompareTag("pit")).ToArray().Length == 1)
             {
                 SetReward(-1f);
-                Done();
+                EndEpisode();
             }
         }
     }
@@ -133,7 +129,7 @@ public override float[] Heuristic()
     }
 
     // to be implemented by the developer
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         area.AreaReset();
     }

Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayAgent.cs

@@ -18,9 +18,8 @@ public class HallwayAgent : Agent
     HallwaySettings m_HallwaySettings;
     int m_Selection;
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
-        base.InitializeAgent();
         m_HallwaySettings = FindObjectOfType<HallwaySettings>();
         m_AgentRb = GetComponent<Rigidbody>();
         m_GroundRenderer = ground.GetComponent<Renderer>();
@@ -67,7 +66,7 @@ public void MoveAgent(float[] act)
         m_AgentRb.AddForce(dirToGo * m_HallwaySettings.agentRunSpeed, ForceMode.VelocityChange);
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         AddReward(-1f / maxStep);
         MoveAgent(vectorAction);
@@ -88,7 +87,7 @@ void OnCollisionEnter(Collision col)
                 SetReward(-0.1f);
                 StartCoroutine(GoalScoredSwapGroundMaterial(m_HallwaySettings.failMaterial, 0.5f));
             }
-            Done();
+            EndEpisode();
         }
     }
 
@@ -113,7 +112,7 @@ public override float[] Heuristic()
         return new float[] { 0 };
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         var agentOffset = -15f;
         var blockOffset = 0f;

Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushAgentBasic.cs

@@ -53,9 +53,8 @@ void Awake()
         m_PushBlockSettings = FindObjectOfType<PushBlockSettings>();
     }
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
-        base.InitializeAgent();
         goalDetect = block.GetComponent<GoalDetect>();
         goalDetect.agent = this;
 
@@ -105,7 +104,7 @@ public void ScoredAGoal()
         AddReward(5f);
 
         // By marking an agent as done AgentReset() will be called automatically.
-        Done();
+        EndEpisode();
 
         // Swap ground material for a bit to indicate we scored.
         StartCoroutine(GoalScoredSwapGroundMaterial(m_PushBlockSettings.goalScoredMaterial, 0.5f));
@@ -161,7 +160,7 @@ public void MoveAgent(float[] act)
     /// <summary>
     /// Called every step of the engine. Here the agent takes an action.
     /// </summary>
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         // Move the agent using the action.
         MoveAgent(vectorAction);
@@ -210,7 +209,7 @@ void ResetBlock()
     /// In the editor, if "Reset On Done" is checked then AgentReset() will be
     /// called automatically anytime we mark done = true in an agent script.
     /// </summary>
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         var rotation = Random.Range(0, 4);
         var rotationAngle = rotation * 90f;

Project/Assets/ML-Agents/Examples/Pyramids/Scripts/PyramidAgent.cs

@@ -14,9 +14,8 @@ public class PyramidAgent : Agent
     public GameObject areaSwitch;
     public bool useVectorObs;
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
-        base.InitializeAgent();
         m_AgentRb = GetComponent<Rigidbody>();
         m_MyArea = area.GetComponent<PyramidArea>();
         m_SwitchLogic = areaSwitch.GetComponent<PyramidSwitch>();
@@ -56,7 +55,7 @@ public void MoveAgent(float[] act)
         m_AgentRb.AddForce(dirToGo * 2f, ForceMode.VelocityChange);
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         AddReward(-1f / maxStep);
         MoveAgent(vectorAction);
@@ -83,7 +82,7 @@ public override float[] Heuristic()
         return new float[] { 0 };
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         var enumerable = Enumerable.Range(0, 9).OrderBy(x => Guid.NewGuid()).Take(9);
         var items = enumerable.ToArray();
@@ -108,7 +107,7 @@ void OnCollisionEnter(Collision collision)
         if (collision.gameObject.CompareTag("goal"))
         {
             SetReward(2f);
-            Done();
+            EndEpisode();
         }
     }
 }

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

@@ -24,7 +24,7 @@ public class ReacherAgent : Agent
     /// Collect the rigidbodies of the reacher in order to resue them for
     /// observations and actions.
     /// </summary>
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_RbA = pendulumA.GetComponent<Rigidbody>();
         m_RbB = pendulumB.GetComponent<Rigidbody>();
@@ -57,7 +57,7 @@ public override void CollectObservations(VectorSensor sensor)
     /// <summary>
     /// The agent's four actions correspond to torques on each of the two joints.
     /// </summary>
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         m_GoalDegree += m_GoalSpeed;
         UpdateGoalPosition();
@@ -86,7 +86,7 @@ void UpdateGoalPosition()
     /// <summary>
     /// Resets the position and velocity of the agent and the goal.
     /// </summary>
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         pendulumA.transform.position = new Vector3(0f, -4f, 0f) + transform.position;
         pendulumA.transform.rotation = Quaternion.Euler(180f, 0f, 0f);

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

@@ -34,7 +34,7 @@ void OnCollisionEnter(Collision col)
 
                 if (agentDoneOnGroundContact)
                 {
-                    agent.Done();
+                    agent.EndEpisode();
                 }
             }
         }

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

@@ -142,7 +142,7 @@ void OverrideModel()
             var nnModel = GetModelForBehaviorName(name);
             Debug.Log($"Overriding behavior {name} for agent with model {nnModel?.name}");
             // This might give a null model; that's better because we'll fall back to the Heuristic
-            m_Agent.GiveModel($"Override_{name}", nnModel);
+            m_Agent.SetModel($"Override_{name}", nnModel);
 
         }
     }