Merge branch 'master' into develop-test-imitation

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

     [Header("Specific to Ball3D")]
     public GameObject ball;
     Rigidbody m_BallRb;
-    IFloatProperties m_ResetParams;
+    FloatPropertiesChannel m_ResetParams;
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_BallRb = ball.GetComponent<Rigidbody>();
         m_ResetParams = Academy.Instance.FloatProperties;
         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);
             Mathf.Abs(ball.transform.position.z - gameObject.transform.position.z) > 3f)
         {
             SetReward(-1f);
-            Done();
+            EndEpisode();
         }
         else
         {
 
-    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

     [Header("Specific to Ball3DHard")]
     public GameObject ball;
     Rigidbody m_BallRb;
-    IFloatProperties m_ResetParams;
+    FloatPropertiesChannel m_ResetParams;
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_BallRb = ball.GetComponent<Rigidbody>();
         m_ResetParams = Academy.Instance.FloatProperties;
         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);
             Mathf.Abs(ball.transform.position.z - gameObject.transform.position.z) > 3f)
         {
             SetReward(-1f);
-            Done();
+            EndEpisode();
         }
         else
         {
 
-    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

         if (m_Position == k_SmallGoalPosition)
         {
             m_Agent.AddReward(0.1f);
-            m_Agent.Done();
+            m_Agent.EndEpisode();
             ResetAgent();
         }
 
-            m_Agent.Done();
+            m_Agent.EndEpisode();
             ResetAgent();
         }
     }

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

     int m_NumberJumps = 20;
     int m_JumpLeft = 20;
 
-    IFloatProperties m_ResetParams;
+    FloatPropertiesChannel m_ResetParams;
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_Rb = gameObject.GetComponent<Rigidbody>();
         m_LookDir = Vector3.zero;
         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++)
         {
         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);
         if (gameObject.transform.position.y < -1)
         {
             AddReward(-1);
-            Done();
+            EndEpisode();
             return;
         }
 
             AddReward(-1);
-            Done();
+            EndEpisode();
-            Done();
+            EndEpisode();
         }
     }
 

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

     Quaternion m_LookRotation;
     Matrix4x4 m_TargetDirMatrix;
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_JdController = GetComponent<JointDriveController>();
         m_DirToTarget = target.position - body.position;
         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;
     /// <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

     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>();
         gameObject.GetComponentInChildren<Renderer>().material = normalMaterial;
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         MoveAgent(vectorAction);
     }
         return action;
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         Unfreeze();
         Unpoison();

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

     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.
     }
 
     // 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]);
             if (hit.Where(col => col.gameObject.CompareTag("goal")).ToArray().Length == 1)
             {
                 SetReward(1f);
-                Done();
+                EndEpisode();
-                Done();
+                EndEpisode();
             }
         }
     }
     }
 
     // to be implemented by the developer
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         area.AreaReset();
     }

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

 
     public GameObject trueAgent;
 
-    IFloatProperties m_ResetParameters;
+    FloatPropertiesChannel m_ResetParameters;
 
     Camera m_AgentCam;
 

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

     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>();
         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);
                 SetReward(-0.1f);
                 StartCoroutine(GoalScoredSwapGroundMaterial(m_HallwaySettings.failMaterial, 0.5f));
             }
-            Done();
+            EndEpisode();
         }
     }
 
         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

         m_PushBlockSettings = FindObjectOfType<PushBlockSettings>();
     }
 
-    public override void InitializeAgent()
+    public override void Initialize()
-        base.InitializeAgent();
         goalDetect = block.GetComponent<GoalDetect>();
         goalDetect.agent = this;
 
         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));
     /// <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);
     /// 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

     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>();
         m_AgentRb.AddForce(dirToGo * 2f, ForceMode.VelocityChange);
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         AddReward(-1f / maxStep);
         MoveAgent(vectorAction);
         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();
         if (collision.gameObject.CompareTag("goal"))
         {
             SetReward(2f);
-            Done();
+            EndEpisode();
         }
     }
 }

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

     /// 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>();
     /// <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();
     /// <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

 
                 if (agentDoneOnGroundContact)
                 {
-                    agent.Done();
+                    agent.EndEpisode();
                 }
             }
         }

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

         void OverrideModel()
         {
             m_Agent.LazyInitialize();
-            var name = m_Agent.BehaviorName;
+            var bp = m_Agent.GetComponent<BehaviorParameters>();
+            var name = bp.behaviorName;
-            m_Agent.GiveModel($"Override_{name}", nnModel);
+            m_Agent.SetModel($"Override_{name}", nnModel);
 
         }
     }

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

     [HideInInspector]
     public Rigidbody agentRb;
     SoccerSettings m_SoccerSettings;
+    BehaviorParameters m_BehaviorParameters;
-    public override void InitializeAgent()
+    public override void Initialize()
-        base.InitializeAgent();
-        if (TeamId == (int)Team.Blue)
+        m_BehaviorParameters = gameObject.GetComponent<BehaviorParameters>();
+        if (m_BehaviorParameters.TeamId == (int)Team.Blue)
         {
             team = Team.Blue;
             m_Transform = new Vector3(transform.position.x - 4f, .5f, transform.position.z);
             ForceMode.VelocityChange);
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         // Existential penalty for strikers.
         AddReward(-1f / 3000f);
         }
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         if (team == Team.Purple)
         {

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

             {
                 ps.agentScript.AddReward(-1);
             }
-            ps.agentScript.Done();  //all agents need to be reset
+            ps.agentScript.EndEpisode();  //all agents need to be reset
 
             if (goalTextUI)
             {

Project/Assets/ML-Agents/Examples/Startup/Scripts/Startup.cs

     internal class Startup : MonoBehaviour
     {
         const string k_SceneVariableName = "SCENE_NAME";
+        private const string k_SceneCommandLineFlag = "--mlagents-scene-name";
-            var sceneName = Environment.GetEnvironmentVariable(k_SceneVariableName);
+            var sceneName = "";
+            
+            // Check for the CLI '--scene-name' flag.  This will be used if
+            // no scene environment variable is found.
+            var args = Environment.GetCommandLineArgs();
+            Console.WriteLine("Command line arguments passed: " + String.Join(" ", args));
+            for (int i = 0; i < args.Length; i++) {
+                if (args [i] == k_SceneCommandLineFlag && i < args.Length - 1) {
+                    sceneName = args[i + 1];
+                }
+            }
+
+            var sceneEnvironmentVariable = Environment.GetEnvironmentVariable(k_SceneVariableName);
+            if (!string.IsNullOrEmpty(sceneEnvironmentVariable))
+            {
+                sceneName = sceneEnvironmentVariable;
+            }
+            
             SwitchScene(sceneName);
         }
 
             {
-                throw new ArgumentException(
-                    $"You didn't specified the {k_SceneVariableName} environment variable");
+                Console.WriteLine(
+                    $"You didn't specify the {k_SceneVariableName} environment variable or the {k_SceneCommandLineFlag} command line argument."
+                );
+                Application.Quit(22);
+                return;
-                throw new ArgumentException(
-                    $"The scene {sceneName} doesn't exist within your build. ");
+                Console.WriteLine(
+                    $"The scene {sceneName} doesn't exist within your build."
+                );
+                Application.Quit(22);
+                return;
             }
             SceneManager.LoadSceneAsync(sceneName);
         }

Project/Assets/ML-Agents/Examples/Template/Scripts/TemplateAgent.cs

     {
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
     }
 }

Project/Assets/ML-Agents/Examples/Tennis/Scripts/HitWall.cs

 
     void Reset()
     {
-        m_AgentA.Done();
-        m_AgentB.Done();
+        m_AgentA.EndEpisode();
+        m_AgentB.EndEpisode();
         m_Area.MatchReset();
         lastFloorHit = FloorHit.Service;
         net = false;

Project/Assets/ML-Agents/Examples/Tennis/Scripts/TennisAgent.cs

     Rigidbody m_AgentRb;
     Rigidbody m_BallRb;
     float m_InvertMult;
-    IFloatProperties m_ResetParams;
+    FloatPropertiesChannel m_ResetParams;
 
     // Looks for the scoreboard based on the name of the gameObjects.
     // Do not modify the names of the Score GameObjects
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_AgentRb = GetComponent<Rigidbody>();
         m_BallRb = ball.GetComponent<Rigidbody>();
         sensor.AddObservation(m_InvertMult * gameObject.transform.rotation.z);
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         var moveX = Mathf.Clamp(vectorAction[0], -1f, 1f) * m_InvertMult;
         var moveY = Mathf.Clamp(vectorAction[1], -1f, 1f);
         return action;
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         m_InvertMult = invertX ? -1f : 1f;
 

Project/Assets/ML-Agents/Examples/Walker/Scripts/WalkerAgent.cs

     Rigidbody m_ChestRb;
     Rigidbody m_SpineRb;
 
-    IFloatProperties m_ResetParams;
+    FloatPropertiesChannel m_ResetParams;
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_JdController = GetComponent<JointDriveController>();
         m_JdController.SetupBodyPart(hips);
         }
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         var bpDict = m_JdController.bodyPartsDict;
         var i = -1;
     /// <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/WallJump/Scripts/WallJumpAgent.cs

     Vector3 m_JumpTargetPos;
     Vector3 m_JumpStartingPos;
 
-    public override void InitializeAgent()
+    public override void Initialize()
     {
         m_WallJumpSettings = FindObjectOfType<WallJumpSettings>();
         m_Configuration = Random.Range(0, 5);
         jumpingTime -= Time.fixedDeltaTime;
     }
 
-    public override void AgentAction(float[] vectorAction)
+    public override void OnActionReceived(float[] vectorAction)
     {
         MoveAgent(vectorAction);
         if ((!Physics.Raycast(m_AgentRb.position, Vector3.down, 20))
-            Done();
+            EndEpisode();
             ResetBlock(m_ShortBlockRb);
             StartCoroutine(
                 GoalScoredSwapGroundMaterial(m_WallJumpSettings.failMaterial, .5f));
         if (col.gameObject.CompareTag("goal") && DoGroundCheck(true))
         {
             SetReward(1f);
-            Done();
+            EndEpisode();
             StartCoroutine(
                 GoalScoredSwapGroundMaterial(m_WallJumpSettings.goalScoredMaterial, 2));
         }
         blockRb.angularVelocity = Vector3.zero;
     }
 
-    public override void AgentReset()
+    public override void OnEpisodeBegin()
     {
         ResetBlock(m_ShortBlockRb);
         transform.localPosition = new Vector3(
                 Academy.Instance.FloatProperties.GetPropertyWithDefault("no_wall_height", 0),
                 localScale.z);
             wall.transform.localScale = localScale;
-            GiveModel("SmallWallJump", noWallBrain);
+            SetModel("SmallWallJump", noWallBrain);
         }
         else if (config == 1)
         {
                 localScale.z);
             wall.transform.localScale = localScale;
-            GiveModel("SmallWallJump", smallWallBrain);
+            SetModel("SmallWallJump", smallWallBrain);
         }
         else
         {
                 height,
                 localScale.z);
             wall.transform.localScale = localScale;
-            GiveModel("BigWallJump", bigWallBrain);
+            SetModel("BigWallJump", bigWallBrain);
         }
     }
 }

README.md

 used for multiple purposes, including controlling NPC behavior (in a variety of
 settings such as multi-agent and adversarial), automated testing of game builds
 and evaluating different game design decisions pre-release. The ML-Agents
-toolkit is mutually beneficial for both game developers and AI researchers as it
+Toolkit is mutually beneficial for both game developers and AI researchers as it
 provides a central platform where advances in AI can be evaluated on Unity’s
 rich environments and then made accessible to the wider research and game
 developer communities.
 * Unity environment control from Python
-* 10+ sample Unity environments
+* 15+ sample Unity environments
 * Two deep reinforcement learning algorithms,
 [Proximal Policy Optimization](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Training-PPO.md)
  (PPO) and [Soft Actor-Critic](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Training-SAC.md)
 * Built-in support for Imitation Learning
 * Flexible agent control with On Demand Decision Making
 * Visualizing network outputs within the environment
-* Simplified set-up with Docker
-## Documentation
+## Releases & Documentation
+**Our latest, stable release is 0.14.1. Click
+[here](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Readme.md) to
+get started with the latest release of ML-Agents.**
+
+The table below lists all our releases, including our `master` branch which is under active
+development and may be unstable. A few helpful guidelines:
+* The docs links in the table below include installation and usage instructions specific to each
+release. Remember to always use the documentation that corresponds to the release version you're
+using.
+* See the [GitHub releases](https://github.com/Unity-Technologies/ml-agents/releases) for more
+details of the changes between versions.
+* If you have used an earlier version of the ML-Agents Toolkit, we strongly recommend our
+[guide on migrating from earlier versions](docs/Migrating.md).
-* For more information, in addition to installation and usage instructions, see
-  the [documentation for the latest release](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Readme.md).
-* If you are a researcher interested in a discussion of Unity as an AI platform, see a pre-print of our [reference paper on Unity and the ML-Agents Toolkit](https://arxiv.org/abs/1809.02627). Also, see below for instructions on citing this paper.
-* If you have used an earlier version of the ML-Agents toolkit, we strongly
-  recommend our [guide on migrating from earlier versions](docs/Migrating.md).
+
+| **Version** | **Release Date** | **Source** | **Documentation** | **Download** |
+|:-------:|:------:|:-------------:|:-------:|:------------:|
+| **master** (unstable) | -- | [source](https://github.com/Unity-Technologies/ml-agents/tree/master) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/master/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/master.zip) |
+| **0.14.1** (latest stable release) | February 26, 2020 | **[source](https://github.com/Unity-Technologies/ml-agents/tree/latest_release)** |  **[docs](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Readme.md)** | **[download](https://github.com/Unity-Technologies/ml-agents/archive/latest_release.zip)** |
+| **0.14.0**  | February 13, 2020 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.14.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.14.0/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.14.0.zip) |
+| **0.13.1**  | January 21, 2020 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.13.1) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.13.1/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.13.1.zip) |
+| **0.13.0**  | January 8, 2020 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.13.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.13.0/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.13.0.zip) |
+| **0.12.1**  | December 11, 2019 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.12.1) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.12.1/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.12.1.zip) |
+| **0.12.0**  | December 2, 2019 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.12.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.12.0/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.12.0.zip) |
+| **0.11.0**  | November 4, 2019 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.11.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.11.0/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.11.0.zip) |
+| **0.10.1**  | October 9, 2019 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.10.1) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.10.1/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.10.1.zip) |
+| **0.10.0**  | September 30, 2019 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.10.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.10.0/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.10.0.zip) |
+
+
+## Citation
+
+If you are a researcher interested in a discussion of Unity as an AI platform, see a pre-print
+of our [reference paper on Unity and the ML-Agents Toolkit](https://arxiv.org/abs/1809.02627).
+
+If you use Unity or the ML-Agents Toolkit to conduct research, we ask that you cite the following
+paper as a reference:
+
+Juliani, A., Berges, V., Vckay, E., Gao, Y., Henry, H., Mattar, M., Lange, D. (2018). Unity: A General Platform for Intelligent Agents. *arXiv preprint arXiv:1809.02627.* https://github.com/Unity-Technologies/ml-agents.
+
-
+* (February 28, 2020) [Training intelligent adversaries using self-play with ML-Agents](https://blogs.unity3d.com/2020/02/28/training-intelligent-adversaries-using-self-play-with-ml-agents/)
+* (November 11, 2019) [Training your agents 7 times faster with ML-Agents](https://blogs.unity3d.com/2019/11/11/training-your-agents-7-times-faster-with-ml-agents/)
+* (October 21, 2019) [The AI@Unity interns help shape the world](https://blogs.unity3d.com/2019/10/21/the-aiunity-interns-help-shape-the-world/)
+* (April 15, 2019) [Unity ML-Agents Toolkit v0.8: Faster training on real games](https://blogs.unity3d.com/2019/04/15/unity-ml-agents-toolkit-v0-8-faster-training-on-real-games/)
+* (March 1, 2019) [Unity ML-Agents Toolkit v0.7: A leap towards cross-platform inference](https://blogs.unity3d.com/2019/03/01/unity-ml-agents-toolkit-v0-7-a-leap-towards-cross-platform-inference/)
+* (December 17, 2018) [ML-Agents Toolkit v0.6: Improved usability of Brains and Imitation Learning](https://blogs.unity3d.com/2018/12/17/ml-agents-toolkit-v0-6-improved-usability-of-brains-and-imitation-learning/)
+* (October 2, 2018) [Puppo, The Corgi: Cuteness Overload with the Unity ML-Agents Toolkit](https://blogs.unity3d.com/2018/10/02/puppo-the-corgi-cuteness-overload-with-the-unity-ml-agents-toolkit/)
+* (September 11, 2018) [ML-Agents Toolkit v0.5, new resources for AI researchers available now](https://blogs.unity3d.com/2018/09/11/ml-agents-toolkit-v0-5-new-resources-for-ai-researchers-available-now/)
+* (June 26, 2018) [Solving sparse-reward tasks with Curiosity](https://blogs.unity3d.com/2018/06/26/solving-sparse-reward-tasks-with-curiosity/)
+* (June 19, 2018) [Unity ML-Agents Toolkit v0.4 and Udacity Deep Reinforcement Learning Nanodegree](https://blogs.unity3d.com/2018/06/19/unity-ml-agents-toolkit-v0-4-and-udacity-deep-reinforcement-learning-nanodegree/)
+* (May 24, 2018) [Imitation Learning in Unity: The Workflow](https://blogs.unity3d.com/2018/05/24/imitation-learning-in-unity-the-workflow/)
+* (March 15, 2018) [ML-Agents Toolkit v0.3 Beta released: Imitation Learning, feedback-driven features, and more](https://blogs.unity3d.com/2018/03/15/ml-agents-v0-3-beta-released-imitation-learning-feedback-driven-features-and-more/)
+* (December 11, 2017) [Using Machine Learning Agents in a real game: a beginner’s guide](https://blogs.unity3d.com/2017/12/11/using-machine-learning-agents-in-a-real-game-a-beginners-guide/)
+* (December 8, 2017) [Introducing ML-Agents Toolkit v0.2: Curriculum Learning, new environments, and more](https://blogs.unity3d.com/2017/12/08/introducing-ml-agents-v0-2-curriculum-learning-new-environments-and-more/)
+* (September 19, 2017) [Introducing: Unity Machine Learning Agents Toolkit](https://blogs.unity3d.com/2017/09/19/introducing-unity-machine-learning-agents/)
-* [Using Machine Learning Agents in a real game: a beginner’s guide](https://blogs.unity3d.com/2017/12/11/using-machine-learning-agents-in-a-real-game-a-beginners-guide/)
-* [Post](https://blogs.unity3d.com/2018/02/28/introducing-the-winners-of-the-first-ml-agents-challenge/)
-  announcing the winners of our
-  [first ML-Agents Challenge](https://connect.unity.com/challenges/ml-agents-1)
-* [Post](https://blogs.unity3d.com/2018/01/23/designing-safer-cities-through-simulations/)
-  overviewing how Unity can be leveraged as a simulator to design safer cities.
 
 In addition to our own documentation, here are some additional, relevant articles:
 
 
 ## Community and Feedback
 
-The ML-Agents toolkit is an open-source project and we encourage and welcome
+The ML-Agents Toolkit is an open-source project and we encourage and welcome
-For problems with the installation and setup of the the ML-Agents toolkit, or
+For problems with the installation and setup of the the ML-Agents Toolkit, or
-If you run into any other problems using the ML-Agents toolkit, or have a specific
+If you run into any other problems using the ML-Agents Toolkit, or have a specific
-Your opinion matters a great deal to us. Only by hearing your thoughts on the Unity ML-Agents Toolkit can we continue
-to improve and grow. Please take a few minutes to [let us know about it](https://github.com/Unity-Technologies/ml-agents/issues/1454).
+Your opinion matters a great deal to us. Only by hearing your thoughts on the Unity ML-Agents
+Toolkit can we continue to improve and grow. Please take a few minutes to
+[let us know about it](https://github.com/Unity-Technologies/ml-agents/issues/1454).
-## Releases
-The latest release is 0.14.1. Previous releases can be found below:
-
-| **Version** | **Source** | **Documentation** | **Download** |
-|:-------:|:------:|:-------------:|:-------:|
-| **0.14.0**  | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.14.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.14.0/docs) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.14.0.zip) |
-| **0.13.1**  | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.13.1) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.13.1/docs) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.13.1.zip) |
-| **0.13.0**  | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.13.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.13.0/docs) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.13.0.zip) |
-| **0.12.1**  | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.12.1) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.12.1/docs) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.12.1.zip) |
-| **0.12.0**  | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.12.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.12.0/docs) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.12.0.zip) |
-| **0.11.0**  | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.11.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.11.0/docs) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.11.0.zip) |
-| **0.10.1**  | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.10.1) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.10.1/docs) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.10.1.zip) |
-| **0.10.0**  | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.10.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.10.0/docs) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.10.0.zip) |
-
-See the [GitHub releases](https://github.com/Unity-Technologies/ml-agents/releases) for more details of the changes
-between versions.
-
-Please note that the `master` branch is under active development, so the documentation there may differ from the code
-of a previous release. Always use the documentation that corresponds to the release version you're using.
-
-## Citation
-
-If you use Unity or the ML-Agents Toolkit to conduct research, we ask that you cite the following paper as a reference:
-
-Juliani, A., Berges, V., Vckay, E., Gao, Y., Henry, H., Mattar, M., Lange, D. (2018). Unity: A General Platform for Intelligent Agents. *arXiv preprint arXiv:1809.02627.* https://github.com/Unity-Technologies/ml-agents.

com.unity.ml-agents/CHANGELOG.md

  - All SideChannel related code has been moved to the namespace `MLAgents.SideChannels`.
  - `BrainParameters` and `SpaceType` have been removed from the public API
  - `BehaviorParameters` have been removed from the public API.
+ - The following methods in the `Agent` class have been deprecated and will be removed in a later release:
+   - `InitializeAgent()` was renamed to `Initialize()`
+   - `AgentAction()` was renamed to `OnActionReceived()`
+   - `AgentReset()` was renamed to `OnEpisodeBegin()`
+   - `Done()` was renamed to `EndEpisode()`
+   - `GiveModel()` was renamed to `SetModel()`
 
 ### Minor Changes
  - Monitor.cs was moved to Examples. (#3372)
  - Academy.RegisterSideChannel and UnregisterSideChannel methods were added. (#3391)
  - A tutorial on adding custom SideChannels was added (#3391)
  - The stepping logic for the Agent and the Academy has been simplified (#3448)
- - Update Barracuda to 0.6.0-preview
+ - Update Barracuda to 0.6.1-preview
  * The interface for `RayPerceptionSensor.PerceiveStatic()` was changed to take an input class and write to an output class, and the method was renamed to `Perceive()`.
  - The checkpoint file suffix was changed from `.cptk` to `.ckpt` (#3470)
  - The command-line argument used to determine the port that an environment will listen on was changed from `--port` to `--mlagents-port`.
  - The method `GetStepCount()` on the Agent class has been replaced with the property getter `StepCount`
  - `RayPerceptionSensorComponent` and related classes now display the debug gizmos whenever the Agent is selected (not just Play mode).
  - Most fields on `RayPerceptionSensorComponent` can now be changed while the editor is in Play mode. The exceptions to this are fields that affect the number of observations.
+ - Most fields on `CameraSensorComponent` and `RenderTextureSensorComponent` were changed to private and replaced by properties with the same name.
-
+ - `DecisionRequester` has been made internal (you can still use the DecisionRequesterComponent from the inspector). `RepeatAction` was renamed `TakeActionsBetweenDecisions` for clarity. (#3555)
+ - The `IFloatProperties` interface has been removed.
+ - Fix #3579.
+ - Improved inference performance for models with multiple action branches. (#3598)
+ - Fixed an issue when using GAIL with less than `batch_size` number of demonstrations. (#3591)
+ - The interfaces to the `SideChannel` classes (on C# and python) have changed to use new  `IncomingMessage` and `OutgoingMessage` classes. These should make reading and writing data to the channel easier. (#3596)
 
 ## [0.14.1-preview] - 2020-02-25
 

com.unity.ml-agents/Documentation~/com.unity.ml-agents.md

-Please see the [ML-Agents README)(https://github.com/Unity-Technologies/ml-agents/blob/master/README.md)
+# About ML-Agents package (`com.unity.ml-agents`)
+
+The Unity ML-Agents package contains the C# SDK for the
+[Unity ML-Agents Toolkit](https://github.com/Unity-Technologies/ml-agents).
+
+The package provides the ability for any Unity scene to be converted into a learning
+environment where character behaviors can be trained using a variety of machine learning
+algorithms. Additionally, it enables any trained behavior to be embedded back into the Unity
+scene. More specifically, the package provides the following core functionalities:
+* Define Agents: entities whose behavior will be learned. Agents are entities
+that generate observations (through sensors), take actions and receive rewards from
+the environment.
+* Define Behaviors: entities that specifiy how an agent should act. Multiple agents can
+share the same Behavior and a scene may have multiple Behaviors.
+* Record demonstrations of an agent within the Editor. These demonstrations can be
+valuable to train a behavior for that agent.
+* Embedding a trained behavior into the scene via the
+[Unity Inference Engine](https://docs.unity3d.com/Packages/com.unity.barracuda@latest/index.html).
+Thus an Agent can switch from a learning behavior to an inference behavior.
+
+Note that this package does not contain the machine learning algorithms for training
+behaviors. It relies on a Python package to orchestrate the training. This package
+only enables instrumenting a Unity scene and setting it up for training, and then
+embedding the trained model back into your Unity scene.
+
+## Preview package
+This package is available as a preview, so it is not ready for production use.
+The features and documentation in this package might change before it is verified for release.
+
+
+## Package contents
+
+The following table describes the package folder structure:
+
+|**Location**|**Description**|
+|---|---|
+|*Documentation~*|Contains the documentation for the Unity package.|
+|*Editor*|Contains utilities for Editor windows and drawers.|
+|*Plugins*|Contains third-party DLLs.|
+|*Runtime*|Contains core C# APIs for integrating ML-Agents into your Unity scene. |
+|*Tests*|Contains the unit tests for the package.|
+
+<a name="Installation"></a>
+
+## Installation
+
+To install this package, follow the instructions in the
+[Package Manager documentation](https://docs.unity3d.com/Manual/upm-ui-install.html).
+
+To install the Python package to enable training behaviors, follow the instructions on our
+[GitHub repository](https://github.com/Unity-Technologies/ml-agents/blob/latest_release/docs/Installation.md).
+
+## Requirements
+
+This version of the Unity ML-Agents package is compatible with the following versions of the Unity Editor:
+
+* 2018.4 and later (recommended)
+
+## Known limitations
+
+### Headless Mode
+
+If you enable Headless mode, you will not be able to collect visual observations
+from your agents.
+
+### Rendering Speed and Synchronization
+
+Currently the speed of the game physics can only be increased to 100x real-time.
+The Academy also moves in time with FixedUpdate() rather than Update(), so game
+behavior implemented in Update() may be out of sync with the agent decision
+making. See
+[Execution Order of Event Functions](https://docs.unity3d.com/Manual/ExecutionOrder.html)
+for more information.
+
+You can control the frequency of Academy stepping by calling
+`Academy.Instance.DisableAutomaticStepping()`, and then calling
+`Academy.Instance.EnvironmentStep()`
+
+### Unity Inference Engine Models
+Currently, only models created with our trainers are supported for running
+ML-Agents with a neural network behavior.
+
+
+## Helpful links
+
+If you are new to the Unity ML-Agents package, or have a question after reading
+the documentation, you can checkout our
+[GitHUb Repository](https://github.com/Unity-Technologies/ml-agents), which
+also includes a number of ways to
+[connect with us](https://github.com/Unity-Technologies/ml-agents#community-and-feedback)
+including our [ML-Agents Forum](https://forum.unity.com/forums/ml-agents.453/).
+

com.unity.ml-agents/Editor/BehaviorParametersEditor.cs

 using UnityEditor;
 using Barracuda;
 using MLAgents.Policies;
+using UnityEngine;
 
 namespace MLAgents.Editor
 {
         {
             var so = serializedObject;
             so.Update();
+            bool needPolicyUpdate; // Whether the name, model, inference device, or BehaviorType changed.
+            EditorGUI.indentLevel++;
+            EditorGUI.BeginChangeCheck(); // global
+
-            EditorGUI.indentLevel++;
-            EditorGUILayout.PropertyField(so.FindProperty("m_BehaviorName"));
-            EditorGUILayout.PropertyField(so.FindProperty("m_BrainParameters"), true);
-            EditorGUILayout.PropertyField(so.FindProperty("m_Model"), true);
-            EditorGUI.indentLevel++;
-            EditorGUILayout.PropertyField(so.FindProperty("m_InferenceDevice"), true);
-            EditorGUI.indentLevel--;
-            EditorGUILayout.PropertyField(so.FindProperty("m_BehaviorType"));
+            {
+                EditorGUILayout.PropertyField(so.FindProperty("m_BehaviorName"));
+            }
+            needPolicyUpdate = EditorGUI.EndChangeCheck();
+
+            EditorGUI.BeginDisabledGroup(Application.isPlaying);
+            {
+                EditorGUILayout.PropertyField(so.FindProperty("m_BrainParameters"), true);
+            }
+            EditorGUI.EndDisabledGroup();
+
+            EditorGUI.BeginChangeCheck();
+            {
+                EditorGUILayout.PropertyField(so.FindProperty("m_Model"), true);
+                EditorGUI.indentLevel++;
+                EditorGUILayout.PropertyField(so.FindProperty("m_InferenceDevice"), true);
+                EditorGUI.indentLevel--;
+            }
+            needPolicyUpdate = needPolicyUpdate || EditorGUI.EndChangeCheck();
+
+            EditorGUI.BeginChangeCheck();
+            {
+                EditorGUILayout.PropertyField(so.FindProperty("m_BehaviorType"));
+            }
+            needPolicyUpdate = needPolicyUpdate || EditorGUI.EndChangeCheck();
+
-            EditorGUILayout.PropertyField(so.FindProperty("m_UseChildSensors"), true);
-            // EditorGUILayout.PropertyField(serializedObject.FindProperty("m_Heuristic"), true);
-            EditorGUI.indentLevel--;
-            if (EditorGUI.EndChangeCheck())
+            EditorGUI.BeginDisabledGroup(Application.isPlaying);
-                m_RequireReload = true;
+                EditorGUILayout.PropertyField(so.FindProperty("m_UseChildSensors"), true);
+            EditorGUI.EndDisabledGroup();
+
+            EditorGUI.indentLevel--;
+            m_RequireReload = EditorGUI.EndChangeCheck();
+
+            if (needPolicyUpdate)
+            {
+                UpdateAgentPolicy();
+            }
         }
 
         /// <summary>
                         EditorGUILayout.HelpBox(check, MessageType.Warning);
                     }
                 }
+            }
+        }
+
+        void UpdateAgentPolicy()
+        {
+            if (Application.isPlaying)
+            {
+                var behaviorParameters = (BehaviorParameters)target;
+                var agent = behaviorParameters.GetComponent<Agent>();
+                if (agent == null)
+                {
+                    return;
+                }
+
+                agent.ReloadPolicy();
+
             }
         }
     }

com.unity.ml-agents/Editor/RayPerceptionSensorComponentBaseEditor.cs

             EditorGUI.BeginChangeCheck();
             EditorGUI.indentLevel++;
 
-            EditorGUILayout.PropertyField(so.FindProperty("m_SensorName"), true);
-
-            // Because the number of rays and the tags affect the observation shape,
-            // they are not editable during play mode.
+            // Don't allow certain fields to be modified during play mode.
+            // * SensorName affects the ordering of the Agent's observations
+            // * The number of tags and rays affects the size of the observations.
+                EditorGUILayout.PropertyField(so.FindProperty("m_SensorName"), true);
                 EditorGUILayout.PropertyField(so.FindProperty("m_DetectableTags"), true);
                 EditorGUILayout.PropertyField(so.FindProperty("m_RaysPerDirection"), true);
             }
                 m_RequireSensorUpdate = true;
             }
 
-            UpdateSensorIfDirty();
+            UpdateSensorIfDirty();
-
-                if (m_RequireSensorUpdate)
-                {
-                    var sensorComponent = serializedObject.targetObject as RayPerceptionSensorComponentBase;
-                    sensorComponent?.UpdateSensor();
-                    m_RequireSensorUpdate = false;
-                }
+            if (m_RequireSensorUpdate)
+            {
+                var sensorComponent = serializedObject.targetObject as RayPerceptionSensorComponentBase;
+                sensorComponent?.UpdateSensor();
+                m_RequireSensorUpdate = false;
+            }
         }
     }
 

com.unity.ml-agents/Runtime/Academy.cs

         /// <summary>
         /// Collection of float properties (indexed by a string).
         /// </summary>
-        public IFloatProperties FloatProperties;
+        public FloatPropertiesChannel FloatProperties;
 
 
         // Fields not provided in the Inspector.

com.unity.ml-agents/Runtime/Agent.cs

             public int maxStep;
         }
 
-        public int TeamId {
-            get {
-                LazyInitialize();
-                return m_PolicyFactory.TeamId;
-                }
-        }
-        public string BehaviorName  {
-            get {
-                LazyInitialize();
-                return m_PolicyFactory.behaviorName;
-                }
-        }
-
         [SerializeField][HideInInspector]
         internal AgentParameters agentParameters;
         [SerializeField][HideInInspector]
         /// </summary>
         internal VectorSensor collectObservationsSensor;
 
-        void OnEnable()
+        /// <summary>
+        /// Called when the attached <see cref="GameObject"/> becomes enabled and active.
+        /// </summary>
+        protected virtual void OnEnable()
         {
             LazyInitialize();
         }
             Academy.Instance.AgentForceReset += _AgentReset;
             m_Brain = m_PolicyFactory.GeneratePolicy(Heuristic);
             ResetData();
-            InitializeAgent();
+            Initialize();
             InitializeSensors();
         }
 
             Disabled,
         }
 
-        void OnDisable()
+        /// <summary>
+        /// Called when the attached <see cref="GameObject"/> becomes disabled and inactive.
+        /// </summary>
+        protected virtual void OnDisable()
         {
             DemonstrationWriters.Clear();
 
             m_Brain?.RequestDecision(m_Info, sensors);
 
             // We also have to write any to any DemonstationStores so that they get the "done" flag.
-            foreach(var demoWriter in DemonstrationWriters)
+            foreach (var demoWriter in DemonstrationWriters)
             {
                 demoWriter.Record(m_Info, sensors);
             }
             m_RequestDecision = false;
         }
 
+        [Obsolete("GiveModel() has been deprecated, use SetModel() instead.")]
+        public void GiveModel(
+            string behaviorName,
+            NNModel model,
+            InferenceDevice inferenceDevice = InferenceDevice.CPU)
+        {
+            SetModel(behaviorName, model, inferenceDevice);
+        }
+
         /// <summary>
         /// Updates the Model for the agent. Any model currently assigned to the
         /// agent will be replaced with the provided one. If the arguments are
         /// <param name="model"> The model to use for inference.</param>
         /// <param name = "inferenceDevice"> Define on what device the model
         /// will be run.</param>
-        public void GiveModel(
+        public void SetModel(
-            m_PolicyFactory.GiveModel(behaviorName, model, inferenceDevice);
+            if (behaviorName == m_PolicyFactory.behaviorName &&
+                model == m_PolicyFactory.model &&
+                inferenceDevice == m_PolicyFactory.inferenceDevice)
+            {
+                // If everything is the same, don't make any changes.
+                return;
+            }
+
+            m_PolicyFactory.model = model;
+            m_PolicyFactory.inferenceDevice = inferenceDevice;
+            m_PolicyFactory.behaviorName = behaviorName;
+            ReloadPolicy();
+        }
+
+        /// <summary>
+        /// Updates the type of behavior for the agent.
+        /// </summary>
+        /// <param name="behaviorType"> The new behaviorType for the Agent.</param>
+        public void SetBehaviorType(BehaviorType behaviorType)
+        {
+            if (m_PolicyFactory.behaviorType == behaviorType)
+            {
+                return;
+            }
+            m_PolicyFactory.behaviorType = behaviorType;
+            ReloadPolicy();
+        }
+
+        internal void ReloadPolicy()
+        {
+
         }
 
         /// <summary>
             TimerStack.Instance.SetGauge(gaugeName, GetCumulativeReward());
         }
 
+        [Obsolete("Done() has been deprecated, use EndEpisode() instead.")]
+        public void Done()
+        {
+            EndEpisode();
+        }
+
-        public void Done()
+        public void EndEpisode()
         {
             NotifyAgentDone(DoneReason.DoneCalled);
             _AgentReset();
             m_RequestAction = true;
         }
 
-
         /// Helper function that resets all the data structures associated with
         /// the agent. Typically used when the agent is being initialized or reset
         /// at the end of an episode.
             // should stay the previous action before the Done(), so that it is properly recorded.
             if (m_Action.vectorActions == null)
             {
-                if (param.vectorActionSpaceType == SpaceType.Continuous)
-                {
-                    m_Action.vectorActions = new float[param.vectorActionSize[0]];
-                    m_Info.storedVectorActions = new float[param.vectorActionSize[0]];
-                }
-                else
-                {
-                    m_Action.vectorActions = new float[param.vectorActionSize.Length];
-                    m_Info.storedVectorActions = new float[param.vectorActionSize.Length];
-                }
+                m_Action.vectorActions = new float[param.numActions];
+                m_Info.storedVectorActions = new float[param.numActions];
+        }
+
+        [Obsolete("InitializeAgent() has been deprecated, use Initialize() instead.")]
+        public virtual void InitializeAgent()
+        {
         }
 
         /// <summary>
         /// One sample use is to store local references to other objects in the
         /// scene which would facilitate computing this agents observation.
         /// </remarks>
-        public virtual void InitializeAgent()
+        public virtual void Initialize()
+#pragma warning disable 0618
+            InitializeAgent();
+#pragma warning restore 0618
         }
 
         /// <summary>
         {
             Debug.LogWarning("Heuristic method called but not implemented. Returning placeholder actions.");
             var param = m_PolicyFactory.brainParameters;
-            var actionSize = param.vectorActionSpaceType == SpaceType.Continuous ?
-                param.vectorActionSize[0] :
-                param.vectorActionSize.Length;
-            return new float[actionSize];
+            return new float[param.numActions];
         }
 
         /// <summary>
         /// </summary>
         void SendInfoToBrain()
         {
+            if (!m_Initialized)
+            {
+                throw new UnityAgentsException("Call to SendInfoToBrain when Agent hasn't been initialized." +
+                    "Please ensure that you are calling 'base.OnEnable()' if you have overridden OnEnable.");
+            }
+
             if (m_Brain == null)
             {
                 return;
             m_Brain.RequestDecision(m_Info, sensors);
 
             // If we have any DemonstrationWriters, write the AgentInfo and sensors to them.
-            foreach(var demoWriter in DemonstrationWriters)
+            foreach (var demoWriter in DemonstrationWriters)
             {
                 demoWriter.Record(m_Info, sensors);
             }
                 sensor.Update();
             }
         }
-
 
         /// <summary>
         /// Collects the vector observations of the agent.
         {