Agent.Heuristic takes an float[] (#3765)

Chris Elion · web-flow · commit 7a6327da79cf · 2020-04-13T11:39:24.000-07:00
diff --git a/Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DAgent.cs b/Project/Assets/ML-Agents/Examples/3DBall/Scripts/Ball3DAgent.cs
@@ -66,13 +66,10 @@ public override void OnEpisodeBegin()
         SetResetParameters();
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
-        var action = new float[2];
-
-        action[0] = -Input.GetAxis("Horizontal");
-        action[1] = Input.GetAxis("Vertical");
-        return action;
+        actionsOut[0] = -Input.GetAxis("Horizontal");
+        actionsOut[1] = Input.GetAxis("Vertical");
     }
 
     public void SetBall()
diff --git a/Project/Assets/ML-Agents/Examples/Bouncer/Scripts/BouncerAgent.cs b/Project/Assets/ML-Agents/Examples/Bouncer/Scripts/BouncerAgent.cs
@@ -102,14 +102,11 @@ void FixedUpdate()
         }
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
-        var action = new float[3];
-
-        action[0] = Input.GetAxis("Horizontal");
-        action[1] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;
-        action[2] = Input.GetAxis("Vertical");
-        return action;
+        actionsOut[0] = Input.GetAxis("Horizontal");
+        actionsOut[1] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;
+        actionsOut[2] = Input.GetAxis("Vertical");
     }
 
     void Update()
diff --git a/Project/Assets/ML-Agents/Examples/FoodCollector/Scripts/FoodCollectorAgent.cs b/Project/Assets/ML-Agents/Examples/FoodCollector/Scripts/FoodCollectorAgent.cs
@@ -207,27 +207,25 @@ public override void OnActionReceived(float[] vectorAction)
         MoveAgent(vectorAction);
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
-        var action = new float[4];
         if (Input.GetKey(KeyCode.D))
         {
-            action[2] = 2f;
+            actionsOut[2] = 2f;
         }
         if (Input.GetKey(KeyCode.W))
         {
-            action[0] = 1f;
+            actionsOut[0] = 1f;
         }
         if (Input.GetKey(KeyCode.A))
         {
-            action[2] = 1f;
+            actionsOut[2] = 1f;
         }
         if (Input.GetKey(KeyCode.S))
         {
-            action[0] = 2f;
+            actionsOut[0] = 2f;
         }
-        action[3] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;
-        return action;
+        actionsOut[3] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;
     }
 
     public override void OnEpisodeBegin()
diff --git a/Project/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAgent.cs b/Project/Assets/ML-Agents/Examples/GridWorld/Scripts/GridAgent.cs
@@ -108,25 +108,25 @@ public override void OnActionReceived(float[] vectorAction)
         }
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
+        actionsOut[0] = k_NoAction;
         if (Input.GetKey(KeyCode.D))
         {
-            return new float[] { k_Right };
+            actionsOut[0] = k_Right;
         }
         if (Input.GetKey(KeyCode.W))
         {
-            return new float[] { k_Up };
+            actionsOut[0] = k_Up;
         }
         if (Input.GetKey(KeyCode.A))
         {
-            return new float[] { k_Left };
+            actionsOut[0] = k_Left;
         }
         if (Input.GetKey(KeyCode.S))
         {
-            return new float[] { k_Down };
+            actionsOut[0] = k_Down;
         }
-        return new float[] { k_NoAction };
     }
 
     // to be implemented by the developer
diff --git a/Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayAgent.cs b/Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayAgent.cs
@@ -91,25 +91,25 @@ void OnCollisionEnter(Collision col)
         }
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
+        actionsOut[0] = 0;
         if (Input.GetKey(KeyCode.D))
         {
-            return new float[] { 3 };
+            actionsOut[0] = 3;
         }
-        if (Input.GetKey(KeyCode.W))
+        else if (Input.GetKey(KeyCode.W))
         {
-            return new float[] { 1 };
+            actionsOut[0] = 1;
         }
-        if (Input.GetKey(KeyCode.A))
+        else if (Input.GetKey(KeyCode.A))
         {
-            return new float[] { 4 };
+            actionsOut[0] = 4;
         }
-        if (Input.GetKey(KeyCode.S))
+        else if (Input.GetKey(KeyCode.S))
         {
-            return new float[] { 2 };
+            actionsOut[0] = 2;
         }
-        return new float[] { 0 };
     }
 
     public override void OnEpisodeBegin()
diff --git a/Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushAgentBasic.cs b/Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushAgentBasic.cs
@@ -170,25 +170,25 @@ public override void OnActionReceived(float[] vectorAction)
         AddReward(-1f / maxStep);
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
+        actionsOut[0] = 0;
         if (Input.GetKey(KeyCode.D))
         {
-            return new float[] { 3 };
+            actionsOut[0] = 3;
         }
-        if (Input.GetKey(KeyCode.W))
+        else if (Input.GetKey(KeyCode.W))
         {
-            return new float[] { 1 };
+            actionsOut[0] = 1;
         }
-        if (Input.GetKey(KeyCode.A))
+        else if (Input.GetKey(KeyCode.A))
         {
-            return new float[] { 4 };
+            actionsOut[0] = 4;
         }
-        if (Input.GetKey(KeyCode.S))
+        else if (Input.GetKey(KeyCode.S))
         {
-            return new float[] { 2 };
+            actionsOut[0] = 2;
         }
-        return new float[] { 0 };
     }
 
     /// <summary>
diff --git a/Project/Assets/ML-Agents/Examples/Pyramids/Scripts/PyramidAgent.cs b/Project/Assets/ML-Agents/Examples/Pyramids/Scripts/PyramidAgent.cs
@@ -61,25 +61,25 @@ public override void OnActionReceived(float[] vectorAction)
         MoveAgent(vectorAction);
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
+        actionsOut[0] = 0;
         if (Input.GetKey(KeyCode.D))
         {
-            return new float[] { 3 };
+            actionsOut[0] = 3;
         }
-        if (Input.GetKey(KeyCode.W))
+        else if (Input.GetKey(KeyCode.W))
         {
-            return new float[] { 1 };
+            actionsOut[0] = 1;
         }
-        if (Input.GetKey(KeyCode.A))
+        else if (Input.GetKey(KeyCode.A))
         {
-            return new float[] { 4 };
+            actionsOut[0] = 4;
         }
-        if (Input.GetKey(KeyCode.S))
+        else if (Input.GetKey(KeyCode.S))
         {
-            return new float[] { 2 };
+            actionsOut[0] = 2;
         }
-        return new float[] { 0 };
     }
 
     public override void OnEpisodeBegin()
diff --git a/Project/Assets/ML-Agents/Examples/Soccer/Scripts/AgentSoccer.cs b/Project/Assets/ML-Agents/Examples/Soccer/Scripts/AgentSoccer.cs
@@ -112,37 +112,35 @@ public override void OnActionReceived(float[] vectorAction)
         MoveAgent(vectorAction);
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
-        var action = new float[3];
         //forward
         if (Input.GetKey(KeyCode.W))
         {
-            action[0] = 1f;
+            actionsOut[0] = 1f;
         }
         if (Input.GetKey(KeyCode.S))
         {
-            action[0] = 2f;
+            actionsOut[0] = 2f;
         }
         //rotate
         if (Input.GetKey(KeyCode.A))
         {
-            action[2] = 1f;
+            actionsOut[2] = 1f;
         }
         if (Input.GetKey(KeyCode.D))
         {
-            action[2] = 2f;
+            actionsOut[2] = 2f;
         }
         //right
         if (Input.GetKey(KeyCode.E))
         {
-            action[1] = 1f;
+            actionsOut[1] = 1f;
         }
         if (Input.GetKey(KeyCode.Q))
         {
-            action[1] = 2f;
+            actionsOut[1] = 2f;
         }
-        return action;
     }
     /// <summary>
     /// Used to provide a "kick" to the ball.
diff --git a/Project/Assets/ML-Agents/Examples/Tennis/Scripts/TennisAgent.cs b/Project/Assets/ML-Agents/Examples/Tennis/Scripts/TennisAgent.cs
@@ -86,14 +86,11 @@ public override void OnActionReceived(float[] vectorAction)
         m_TextComponent.text = score.ToString();
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
-        var action = new float[3];
-
-        action[0] = Input.GetAxis("Horizontal");    // Racket Movement
-        action[1] = Input.GetKey(KeyCode.Space) ? 1f : 0f;   // Racket Jumping
-        action[2] = Input.GetAxis("Vertical");   // Racket Rotation  
-        return action;
+        actionsOut[0] = Input.GetAxis("Horizontal");    // Racket Movement
+        actionsOut[1] = Input.GetKey(KeyCode.Space) ? 1f : 0f;   // Racket Jumping
+        actionsOut[2] = Input.GetAxis("Vertical");   // Racket Rotation
     }
 
     public override void OnEpisodeBegin()
diff --git a/Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs b/Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs
@@ -241,27 +241,25 @@ public override void OnActionReceived(float[] vectorAction)
         }
     }
 
-    public override float[] Heuristic()
+    public override void Heuristic(float[] actionsOut)
     {
-        var action = new float[4];
         if (Input.GetKey(KeyCode.D))
         {
-            action[1] = 2f;
+            actionsOut[1] = 2f;
         }
         if (Input.GetKey(KeyCode.W))
         {
-            action[0] = 1f;
+            actionsOut[0] = 1f;
         }
         if (Input.GetKey(KeyCode.A))
         {
-            action[1] = 1f;
+            actionsOut[1] = 1f;
         }
         if (Input.GetKey(KeyCode.S))
         {
-            action[0] = 2f;
+            actionsOut[0] = 2f;
         }
-        action[3] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;
-        return action;
+        actionsOut[3] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;
     }
 
     // Detect when the agent hits the goal
diff --git a/com.unity.ml-agents/CHANGELOG.md b/com.unity.ml-agents/CHANGELOG.md
@@ -17,6 +17,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
  - Added ability to start training (initialize model weights) from a previous run ID. (#3710)
  - The internal event `Academy.AgentSetStatus` was renamed to `Academy.AgentPreStep` and made public.
  - The offset logic was removed from DecisionRequester.
+ - The signature of `Agent.Heuristic()` was changed to take a `float[]` as a parameter, instead of returning the array. This was done to prevent a common source of error where users would return arrays of the wrong size.
  - The communication API version has been bumped up to 1.0.0 and will use [Semantic Versioning](https://semver.org/) to do compatibility checks for communication between Unity and the Python process.
 
 ### Minor Changes
diff --git a/com.unity.ml-agents/Runtime/Agent.cs b/com.unity.ml-agents/Runtime/Agent.cs
@@ -547,12 +547,10 @@ public virtual void Initialize()
         /// </summary>
         /// <returns> A float array corresponding to the next action of the Agent
         /// </returns>
-        public virtual float[] Heuristic()
+        public virtual void Heuristic(float[] actionsOut)
         {
             Debug.LogWarning("Heuristic method called but not implemented. Returning placeholder actions.");
-            var param = m_PolicyFactory.brainParameters;
-
-            return new float[param.numActions];
+            Array.Clear(actionsOut, 0, actionsOut.Length);
         }
 
         /// <summary>
diff --git a/com.unity.ml-agents/Runtime/Policies/BehaviorParameters.cs b/com.unity.ml-agents/Runtime/Policies/BehaviorParameters.cs
@@ -135,12 +135,12 @@ public string fullyQualifiedBehaviorName
             get { return m_BehaviorName + "?team=" + TeamId; }
         }
 
-        internal IPolicy GeneratePolicy(Func<float[]> heuristic)
+        internal IPolicy GeneratePolicy(HeuristicPolicy.ActionGenerator heuristic)
         {
             switch (m_BehaviorType)
             {
                 case BehaviorType.HeuristicOnly:
-                    return new HeuristicPolicy(heuristic);
+                    return new HeuristicPolicy(heuristic, m_BrainParameters.numActions);
                 case BehaviorType.InferenceOnly:
                 {
                     if (m_Model == null)
@@ -164,10 +164,10 @@ internal IPolicy GeneratePolicy(Func<float[]> heuristic)
                     }
                     else
                     {
-                        return new HeuristicPolicy(heuristic);
+                        return new HeuristicPolicy(heuristic, m_BrainParameters.numActions);
                     }
                 default:
-                    return new HeuristicPolicy(heuristic);
+                    return new HeuristicPolicy(heuristic, m_BrainParameters.numActions);
             }
         }
 
diff --git a/com.unity.ml-agents/Runtime/Policies/HeuristicPolicy.cs b/com.unity.ml-agents/Runtime/Policies/HeuristicPolicy.cs
@@ -12,17 +12,20 @@ namespace MLAgents.Policies
     /// </summary>
     internal class HeuristicPolicy : IPolicy
     {
-        Func<float[]> m_Heuristic;
+        public delegate void ActionGenerator(float[] actionsOut);
+        ActionGenerator m_Heuristic;
         float[] m_LastDecision;
+        int m_numActions;
 
         WriteAdapter m_WriteAdapter = new WriteAdapter();
         NullList m_NullList = new NullList();
 
 
         /// <inheritdoc />
-        public HeuristicPolicy(Func<float[]> heuristic)
+        public HeuristicPolicy(ActionGenerator heuristic, int numActions)
         {
             m_Heuristic = heuristic;
+            m_numActions = numActions;
         }
 
         /// <inheritdoc />
@@ -31,7 +34,9 @@ public void RequestDecision(AgentInfo info, List<ISensor> sensors)
             StepSensors(sensors);
             if (!info.done)
             {
-                m_LastDecision = m_Heuristic.Invoke();
+                // Reset m_LastDecision each time.
+                 m_LastDecision = new float[m_numActions];
+                 m_Heuristic.Invoke(m_LastDecision);
             }
         }
 
diff --git a/com.unity.ml-agents/Tests/Editor/BehaviorParameterTests.cs b/com.unity.ml-agents/Tests/Editor/BehaviorParameterTests.cs
diff --git a/com.unity.ml-agents/Tests/Editor/MLAgentsEditModeTest.cs b/com.unity.ml-agents/Tests/Editor/MLAgentsEditModeTest.cs
diff --git a/com.unity.ml-agents/Tests/Runtime/RuntimeAPITest.cs b/com.unity.ml-agents/Tests/Runtime/RuntimeAPITest.cs
diff --git a/docs/Getting-Started.md b/docs/Getting-Started.md
diff --git a/docs/Learning-Environment-Create-New.md b/docs/Learning-Environment-Create-New.md
diff --git a/docs/Learning-Environment-Design-Agents.md b/docs/Learning-Environment-Design-Agents.md
diff --git a/docs/Migrating.md b/docs/Migrating.md

Original file line number	Diff line number	Diff line change
`@@ -66,13 +66,10 @@ public override void OnEpisodeBegin()`
`66`	`66`	`SetResetParameters();`
`67`	`67`	`}`
`68`	`68`
`69`		`- public override float[] Heuristic()`
	`69`	`+ public override void Heuristic(float[] actionsOut)`
`70`	`70`	`{`
`71`		`- var action = new float[2];`
`72`		`-`
`73`		`- action[0] = -Input.GetAxis("Horizontal");`
`74`		`- action[1] = Input.GetAxis("Vertical");`
`75`		`- return action;`
	`71`	`+ actionsOut[0] = -Input.GetAxis("Horizontal");`
	`72`	`+ actionsOut[1] = Input.GetAxis("Vertical");`
`76`	`73`	`}`
`77`	`74`
`78`	`75`	`public void SetBall()`
Original file line number	Diff line number	Diff line change
`@@ -102,14 +102,11 @@ void FixedUpdate()`
`102`	`102`	`}`
`103`	`103`	`}`
`104`	`104`
`105`		`- public override float[] Heuristic()`
	`105`	`+ public override void Heuristic(float[] actionsOut)`
`106`	`106`	`{`
`107`		`- var action = new float[3];`
`108`		`-`
`109`		`- action[0] = Input.GetAxis("Horizontal");`
`110`		`- action[1] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;`
`111`		`- action[2] = Input.GetAxis("Vertical");`
`112`		`- return action;`
	`107`	`+ actionsOut[0] = Input.GetAxis("Horizontal");`
	`108`	`+ actionsOut[1] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;`
	`109`	`+ actionsOut[2] = Input.GetAxis("Vertical");`
`113`	`110`	`}`
`114`	`111`
`115`	`112`	`void Update()`
Original file line number	Diff line number	Diff line change
`@@ -207,27 +207,25 @@ public override void OnActionReceived(float[] vectorAction)`
`207`	`207`	`MoveAgent(vectorAction);`
`208`	`208`	`}`
`209`	`209`
`210`		`- public override float[] Heuristic()`
	`210`	`+ public override void Heuristic(float[] actionsOut)`
`211`	`211`	`{`
`212`		`- var action = new float[4];`
`213`	`212`	`if (Input.GetKey(KeyCode.D))`
`214`	`213`	`{`
`215`		`- action[2] = 2f;`
	`214`	`+ actionsOut[2] = 2f;`
`216`	`215`	`}`
`217`	`216`	`if (Input.GetKey(KeyCode.W))`
`218`	`217`	`{`
`219`		`- action[0] = 1f;`
	`218`	`+ actionsOut[0] = 1f;`
`220`	`219`	`}`
`221`	`220`	`if (Input.GetKey(KeyCode.A))`
`222`	`221`	`{`
`223`		`- action[2] = 1f;`
	`222`	`+ actionsOut[2] = 1f;`
`224`	`223`	`}`
`225`	`224`	`if (Input.GetKey(KeyCode.S))`
`226`	`225`	`{`
`227`		`- action[0] = 2f;`
	`226`	`+ actionsOut[0] = 2f;`
`228`	`227`	`}`
`229`		`- action[3] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;`
`230`		`- return action;`
	`228`	`+ actionsOut[3] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;`
`231`	`229`	`}`
`232`	`230`
`233`	`231`	`public override void OnEpisodeBegin()`
Original file line number	Diff line number	Diff line change
`@@ -108,25 +108,25 @@ public override void OnActionReceived(float[] vectorAction)`
`108`	`108`	`}`
`109`	`109`	`}`
`110`	`110`
`111`		`- public override float[] Heuristic()`
	`111`	`+ public override void Heuristic(float[] actionsOut)`
`112`	`112`	`{`
	`113`	`+ actionsOut[0] = k_NoAction;`
`113`	`114`	`if (Input.GetKey(KeyCode.D))`
`114`	`115`	`{`
`115`		`- return new float[] { k_Right };`
	`116`	`+ actionsOut[0] = k_Right;`
`116`	`117`	`}`
`117`	`118`	`if (Input.GetKey(KeyCode.W))`
`118`	`119`	`{`
`119`		`- return new float[] { k_Up };`
	`120`	`+ actionsOut[0] = k_Up;`
`120`	`121`	`}`
`121`	`122`	`if (Input.GetKey(KeyCode.A))`
`122`	`123`	`{`
`123`		`- return new float[] { k_Left };`
	`124`	`+ actionsOut[0] = k_Left;`
`124`	`125`	`}`
`125`	`126`	`if (Input.GetKey(KeyCode.S))`
`126`	`127`	`{`
`127`		`- return new float[] { k_Down };`
	`128`	`+ actionsOut[0] = k_Down;`
`128`	`129`	`}`
`129`		`- return new float[] { k_NoAction };`
`130`	`130`	`}`
`131`	`131`
`132`	`132`	`// to be implemented by the developer`
Original file line number	Diff line number	Diff line change
`@@ -91,25 +91,25 @@ void OnCollisionEnter(Collision col)`
`91`	`91`	`}`
`92`	`92`	`}`
`93`	`93`
`94`		`- public override float[] Heuristic()`
	`94`	`+ public override void Heuristic(float[] actionsOut)`
`95`	`95`	`{`
	`96`	`+ actionsOut[0] = 0;`
`96`	`97`	`if (Input.GetKey(KeyCode.D))`
`97`	`98`	`{`
`98`		`- return new float[] { 3 };`
	`99`	`+ actionsOut[0] = 3;`
`99`	`100`	`}`
`100`		`- if (Input.GetKey(KeyCode.W))`
	`101`	`+ else if (Input.GetKey(KeyCode.W))`
`101`	`102`	`{`
`102`		`- return new float[] { 1 };`
	`103`	`+ actionsOut[0] = 1;`
`103`	`104`	`}`
`104`		`- if (Input.GetKey(KeyCode.A))`
	`105`	`+ else if (Input.GetKey(KeyCode.A))`
`105`	`106`	`{`
`106`		`- return new float[] { 4 };`
	`107`	`+ actionsOut[0] = 4;`
`107`	`108`	`}`
`108`		`- if (Input.GetKey(KeyCode.S))`
	`109`	`+ else if (Input.GetKey(KeyCode.S))`
`109`	`110`	`{`
`110`		`- return new float[] { 2 };`
	`111`	`+ actionsOut[0] = 2;`
`111`	`112`	`}`
`112`		`- return new float[] { 0 };`
`113`	`113`	`}`
`114`	`114`
`115`	`115`	`public override void OnEpisodeBegin()`
Original file line number	Diff line number	Diff line change
`@@ -170,25 +170,25 @@ public override void OnActionReceived(float[] vectorAction)`
`170`	`170`	`AddReward(-1f / maxStep);`
`171`	`171`	`}`
`172`	`172`
`173`		`- public override float[] Heuristic()`
	`173`	`+ public override void Heuristic(float[] actionsOut)`
`174`	`174`	`{`
	`175`	`+ actionsOut[0] = 0;`
`175`	`176`	`if (Input.GetKey(KeyCode.D))`
`176`	`177`	`{`
`177`		`- return new float[] { 3 };`
	`178`	`+ actionsOut[0] = 3;`
`178`	`179`	`}`
`179`		`- if (Input.GetKey(KeyCode.W))`
	`180`	`+ else if (Input.GetKey(KeyCode.W))`
`180`	`181`	`{`
`181`		`- return new float[] { 1 };`
	`182`	`+ actionsOut[0] = 1;`
`182`	`183`	`}`
`183`		`- if (Input.GetKey(KeyCode.A))`
	`184`	`+ else if (Input.GetKey(KeyCode.A))`
`184`	`185`	`{`
`185`		`- return new float[] { 4 };`
	`186`	`+ actionsOut[0] = 4;`
`186`	`187`	`}`
`187`		`- if (Input.GetKey(KeyCode.S))`
	`188`	`+ else if (Input.GetKey(KeyCode.S))`
`188`	`189`	`{`
`189`		`- return new float[] { 2 };`
	`190`	`+ actionsOut[0] = 2;`
`190`	`191`	`}`
`191`		`- return new float[] { 0 };`
`192`	`192`	`}`
`193`	`193`
`194`	`194`	`/// <summary>`
Original file line number	Diff line number	Diff line change
`@@ -61,25 +61,25 @@ public override void OnActionReceived(float[] vectorAction)`
`61`	`61`	`MoveAgent(vectorAction);`
`62`	`62`	`}`
`63`	`63`
`64`		`- public override float[] Heuristic()`
	`64`	`+ public override void Heuristic(float[] actionsOut)`
`65`	`65`	`{`
	`66`	`+ actionsOut[0] = 0;`
`66`	`67`	`if (Input.GetKey(KeyCode.D))`
`67`	`68`	`{`
`68`		`- return new float[] { 3 };`
	`69`	`+ actionsOut[0] = 3;`
`69`	`70`	`}`
`70`		`- if (Input.GetKey(KeyCode.W))`
	`71`	`+ else if (Input.GetKey(KeyCode.W))`
`71`	`72`	`{`
`72`		`- return new float[] { 1 };`
	`73`	`+ actionsOut[0] = 1;`
`73`	`74`	`}`
`74`		`- if (Input.GetKey(KeyCode.A))`
	`75`	`+ else if (Input.GetKey(KeyCode.A))`
`75`	`76`	`{`
`76`		`- return new float[] { 4 };`
	`77`	`+ actionsOut[0] = 4;`
`77`	`78`	`}`
`78`		`- if (Input.GetKey(KeyCode.S))`
	`79`	`+ else if (Input.GetKey(KeyCode.S))`
`79`	`80`	`{`
`80`		`- return new float[] { 2 };`
	`81`	`+ actionsOut[0] = 2;`
`81`	`82`	`}`
`82`		`- return new float[] { 0 };`
`83`	`83`	`}`
`84`	`84`
`85`	`85`	`public override void OnEpisodeBegin()`
Original file line number	Diff line number	Diff line change
`@@ -112,37 +112,35 @@ public override void OnActionReceived(float[] vectorAction)`
`112`	`112`	`MoveAgent(vectorAction);`
`113`	`113`	`}`
`114`	`114`
`115`		`- public override float[] Heuristic()`
	`115`	`+ public override void Heuristic(float[] actionsOut)`
`116`	`116`	`{`
`117`		`- var action = new float[3];`
`118`	`117`	`//forward`
`119`	`118`	`if (Input.GetKey(KeyCode.W))`
`120`	`119`	`{`
`121`		`- action[0] = 1f;`
	`120`	`+ actionsOut[0] = 1f;`
`122`	`121`	`}`
`123`	`122`	`if (Input.GetKey(KeyCode.S))`
`124`	`123`	`{`
`125`		`- action[0] = 2f;`
	`124`	`+ actionsOut[0] = 2f;`
`126`	`125`	`}`
`127`	`126`	`//rotate`
`128`	`127`	`if (Input.GetKey(KeyCode.A))`
`129`	`128`	`{`
`130`		`- action[2] = 1f;`
	`129`	`+ actionsOut[2] = 1f;`
`131`	`130`	`}`
`132`	`131`	`if (Input.GetKey(KeyCode.D))`
`133`	`132`	`{`
`134`		`- action[2] = 2f;`
	`133`	`+ actionsOut[2] = 2f;`
`135`	`134`	`}`
`136`	`135`	`//right`
`137`	`136`	`if (Input.GetKey(KeyCode.E))`
`138`	`137`	`{`
`139`		`- action[1] = 1f;`
	`138`	`+ actionsOut[1] = 1f;`
`140`	`139`	`}`
`141`	`140`	`if (Input.GetKey(KeyCode.Q))`
`142`	`141`	`{`
`143`		`- action[1] = 2f;`
	`142`	`+ actionsOut[1] = 2f;`
`144`	`143`	`}`
`145`		`- return action;`
`146`	`144`	`}`
`147`	`145`	`/// <summary>`
`148`	`146`	`/// Used to provide a "kick" to the ball.`
Original file line number	Diff line number	Diff line change
`@@ -86,14 +86,11 @@ public override void OnActionReceived(float[] vectorAction)`
`86`	`86`	`m_TextComponent.text = score.ToString();`
`87`	`87`	`}`
`88`	`88`
`89`		`- public override float[] Heuristic()`
	`89`	`+ public override void Heuristic(float[] actionsOut)`
`90`	`90`	`{`
`91`		`- var action = new float[3];`
`92`		`-`
`93`		`- action[0] = Input.GetAxis("Horizontal"); // Racket Movement`
`94`		`- action[1] = Input.GetKey(KeyCode.Space) ? 1f : 0f; // Racket Jumping`
`95`		`- action[2] = Input.GetAxis("Vertical"); // Racket Rotation`
`96`		`- return action;`
	`91`	`+ actionsOut[0] = Input.GetAxis("Horizontal"); // Racket Movement`
	`92`	`+ actionsOut[1] = Input.GetKey(KeyCode.Space) ? 1f : 0f; // Racket Jumping`
	`93`	`+ actionsOut[2] = Input.GetAxis("Vertical"); // Racket Rotation`
`97`	`94`	`}`
`98`	`95`
`99`	`96`	`public override void OnEpisodeBegin()`
Original file line number	Diff line number	Diff line change
`@@ -241,27 +241,25 @@ public override void OnActionReceived(float[] vectorAction)`
`241`	`241`	`}`
`242`	`242`	`}`
`243`	`243`
`244`		`- public override float[] Heuristic()`
	`244`	`+ public override void Heuristic(float[] actionsOut)`
`245`	`245`	`{`
`246`		`- var action = new float[4];`
`247`	`246`	`if (Input.GetKey(KeyCode.D))`
`248`	`247`	`{`
`249`		`- action[1] = 2f;`
	`248`	`+ actionsOut[1] = 2f;`
`250`	`249`	`}`
`251`	`250`	`if (Input.GetKey(KeyCode.W))`
`252`	`251`	`{`
`253`		`- action[0] = 1f;`
	`252`	`+ actionsOut[0] = 1f;`
`254`	`253`	`}`
`255`	`254`	`if (Input.GetKey(KeyCode.A))`
`256`	`255`	`{`
`257`		`- action[1] = 1f;`
	`256`	`+ actionsOut[1] = 1f;`
`258`	`257`	`}`
`259`	`258`	`if (Input.GetKey(KeyCode.S))`
`260`	`259`	`{`
`261`		`- action[0] = 2f;`
	`260`	`+ actionsOut[0] = 2f;`
`262`	`261`	`}`
`263`		`- action[3] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;`
`264`		`- return action;`
	`262`	`+ actionsOut[3] = Input.GetKey(KeyCode.Space) ? 1.0f : 0.0f;`
`265`	`263`	`}`
`266`	`264`
`267`	`265`	`// Detect when the agent hits the goal`