Merge remote-tracking branch 'origin/master' into develop-add-fire

# Conflicts:
#	ml-agents/mlagents/trainers/policy/tf_policy.py

.circleci/config.yml

       directory:
         type: string
         description: Local directory to use for publishing (e.g. ml-agents)
+      username:
+        type: string
+        description: pypi username
+        default: mlagents
+      test_repository_args:
+        type: string
+        description: Optional override repository URL. Only use for tests, leave blank for "real"
+        default: ""
     docker:
       - image: circleci/python:3.6
     steps:
           command: |
             . venv/bin/activate
             cd << parameters.directory >>
-            twine upload -u mlagents -p $PYPI_PASSWORD dist/*
+            twine upload -u << parameters.username >> -p $PYPI_PASSWORD << parameters.test_repository_args >> dist/*
 
 workflows:
   version: 2
           pip_constraints: test_constraints_max_tf2_version.txt
       - markdown_link_check
       - pre-commit
+      # The first deploy jobs are the "real" ones that upload to pypi
-              only: /[0-9]+(\.[0-9]+)*(\.dev[0-9]+)*/
+              # Matches e.g. "release_123"
+              only: /^release_[0-9]+$/
             branches:
               ignore: /.*/
       - deploy:
             tags:
-              only: /[0-9]+(\.[0-9]+)*(\.dev[0-9]+)*/
+              # Matches e.g. "release_123"
+              only: /^release_[0-9]+$/
             branches:
               ignore: /.*/
       - deploy:
             tags:
-              only: /[0-9]+(\.[0-9]+)*(\.dev[0-9]+)*/
+              # Matches e.g. "release_123"
+              only: /^release_[0-9]+$/
+            branches:
+              ignore: /.*/
+      # These deploy jobs upload to the pypi test repo. They have different tag triggers than the real ones.
+      - deploy:
+          name: test deploy ml-agents-envs
+          directory: ml-agents-envs
+          username: mlagents-test
+          test_repository_args: --repository-url https://test.pypi.org/legacy/
+          filters:
+            tags:
+              # Matches e.g. "release_123_test456
+              only: /^release_[0-9]+_test[0-9]+$/
+            branches:
+              ignore: /.*/
+      - deploy:
+          name: test deploy ml-agents
+          directory: ml-agents
+          username: mlagents-test
+          test_repository_args: --repository-url https://test.pypi.org/legacy/
+          filters:
+            tags:
+              # Matches e.g. "release_123_test456
+              only: /^release_[0-9]+_test[0-9]+$/
+            branches:
+              ignore: /.*/
+      - deploy:
+          name: test deploy gym-unity
+          directory: gym-unity
+          username: mlagents-test
+          test_repository_args: --repository-url https://test.pypi.org/legacy/
+          filters:
+            tags:
+              # Matches e.g. "release_123_test456
+              only: /^release_[0-9]+_test[0-9]+$/
             branches:
               ignore: /.*/
   nightly:

.gitignore

-# Tensorflow Model Info
+# Output Artifacts (Legacy)
+# Output Artifacts
+/results
 
 # Training environments
 /envs

.pylintrc

 
     # Using the global statement
     W0603,
+
+    # "Access to a protected member _foo of a client class (protected-access)"
+    W0212

.yamato/training-int-tests.yml

     # Backwards-compatibility tests.
     # If we make a breaking change to the communication protocol, these will need
     # to be disabled until the next release.
-    # - python -u -m ml-agents.tests.yamato.training_int_tests --python=0.15.0
-    # - python -u -m ml-agents.tests.yamato.training_int_tests --csharp=0.15.0
+    - python -u -m ml-agents.tests.yamato.training_int_tests --python=0.16.0
+    - python -u -m ml-agents.tests.yamato.training_int_tests --csharp=1.0.0
   dependencies:
     - .yamato/standalone-build-test.yml#test_mac_standalone_{{ editor.version }}
   triggers:

Project/Assets/ML-Agents/Editor/Tests/StandaloneBuildTest.cs

 using UnityEngine;
 using UnityEditor.Build.Reporting;
 
-namespace MLAgents
+namespace Unity.MLAgents
-        const string k_outputCommandLineFlag = "--mlagents-build-output-path";
-        const string k_sceneCommandLineFlag = "--mlagents-build-scene-path";
+        const string k_OutputCommandLineFlag = "--mlagents-build-output-path";
+        const string k_SceneCommandLineFlag = "--mlagents-build-scene-path";
 
         public static void BuildStandalonePlayerOSX()
         {
             var args = Environment.GetCommandLineArgs();
             for (var i = 0; i < args.Length - 1; i++)
             {
-                if (args[i] == k_outputCommandLineFlag)
+                if (args[i] == k_OutputCommandLineFlag)
-                else if (args[i] == k_sceneCommandLineFlag)
+                else if (args[i] == k_SceneCommandLineFlag)
                 {
                     scenePath = args[i + 1];
                 }

Project/Assets/ML-Agents/Examples/3DBall/Demos/Expert3DBall.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/3DBall/Demos/Expert3DBall.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

Project/Assets/ML-Agents/Examples/3DBall/Demos/Expert3DBallHard.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/3DBall/Demos/Expert3DBallHard.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using UnityEngine;
-using MLAgents;
-using MLAgents.Sensors;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
+using Unity.MLAgents.Sensors;
 
 public class Ball3DAgent : Agent
 {

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

 using UnityEngine;
-using MLAgents;
-using MLAgents.Sensors;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
+using Unity.MLAgents.Sensors;
 
 public class Ball3DHardAgent : Agent
 {

Project/Assets/ML-Agents/Examples/Basic/Demos/ExpertBasic.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/Basic/Demos/ExpertBasic.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using UnityEngine;
 using UnityEngine.SceneManagement;
-using MLAgents;
+using Unity.MLAgents;
+using UnityEngine.Serialization;
 
 /// <summary>
 /// An example of how to use ML-Agents without inheriting from the Agent class.
 {
     public float timeBetweenDecisionsAtInference;
     float m_TimeSinceDecision;
+    [FormerlySerializedAs("m_Position")]
-    public int m_Position;
+    public int position;
     const int k_SmallGoalPosition = 7;
     const int k_LargeGoalPosition = 17;
     public GameObject largeGoal;
     public void OnEnable()
     {
         m_Agent = GetComponent<Agent>();
-        m_Position = 10;
-        transform.position = new Vector3(m_Position - 10f, 0f, 0f);
+        position = 10;
+        transform.position = new Vector3(position - 10f, 0f, 0f);
         smallGoal.transform.position = new Vector3(k_SmallGoalPosition - 10f, 0f, 0f);
         largeGoal.transform.position = new Vector3(k_LargeGoalPosition - 10f, 0f, 0f);
     }
                 break;
         }
 
-        m_Position += direction;
-        if (m_Position < k_MinPosition) { m_Position = k_MinPosition; }
-        if (m_Position > k_MaxPosition) { m_Position = k_MaxPosition; }
+        position += direction;
+        if (position < k_MinPosition) { position = k_MinPosition; }
+        if (position > k_MaxPosition) { position = k_MaxPosition; }
-        gameObject.transform.position = new Vector3(m_Position - 10f, 0f, 0f);
+        gameObject.transform.position = new Vector3(position - 10f, 0f, 0f);
-        if (m_Position == k_SmallGoalPosition)
+        if (position == k_SmallGoalPosition)
         {
             m_Agent.AddReward(0.1f);
             m_Agent.EndEpisode();
-        if (m_Position == k_LargeGoalPosition)
+        if (position == k_LargeGoalPosition)
         {
             m_Agent.AddReward(1f);
             m_Agent.EndEpisode();
 
     public void ResetAgent()
-    {   
+    {
         // This is a very inefficient way to reset the scene. Used here for testing.
         SceneManager.LoadScene(SceneManager.GetActiveScene().name);
         m_Agent = null; // LoadScene only takes effect at the next Update.

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

 using System;
-using MLAgents.Sensors;
-using UnityEngine.Serialization;
+using Unity.MLAgents.Sensors;
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     /// <summary>
     /// A simple example of a SensorComponent.
         {
             // One-hot encoding of the position
             Array.Clear(output, 0, output.Length);
-            output[basicController.m_Position] = 1;
+            output[basicController.position] = 1;
         }
 
         /// <inheritdoc/>

Project/Assets/ML-Agents/Examples/Basic/TFModels/Basic.nn

-vector_observation����

action_masks����

policy_1/concat_2/concatactionaction_output_shape������?action_output_shape




memory_size





version_number




is_continuous_control




policy_1/add_2/y




policy_1/add/y




policy_1/Sum/reduction_indices




$policy/main_graph_0/hidden_0/BiasAdd
�����?
vector_observation#policy/main_graph_0/hidden_0/kernel

�
!policy/main_graph_0/hidden_0/bias


�
 policy/main_graph_0/hidden_0/Mul2	�����?
$policy/main_graph_0/hidden_0/BiasAddpolicy_1/dense/MatMul
�����?
 policy/main_graph_0/hidden_0/Mulpolicy/dense/kernel

�
<policy_1/dense/MatMul/patch:0


�
policy_1/strided_slice�



�����?
action_maskspolicy_1/Softmax2�����?
policy_1/dense/MatMulpolicy_1/addd�����?policy_1/Softmaxpolicy_1/add/ypolicy_1/Mulf�����?policy_1/addpolicy_1/strided_slicepolicy_1/Sum������?policy_1/Mulpolicy_1/Sum/reduction_indicespolicy_1/truedivg�����?policy_1/Mulpolicy_1/Sumpolicy_1/add_2d�����?policy_1/truedivpolicy_1/add_2/ypolicy_1/Log_12r�����?
policy_1/add_2policy_1/concat_2/concat2�����?
policy_1/Log_1action2�����?
policy_1/concat_2/concat@@@���3���3�?������>C�{>�����>M��;D�o�X|6>�q*>n����l?낝>>d=�ߓ���u�ȹ�<��"��8��cw�>��l�ʉ�>���="�����>�#�<�=���€�Ka����>aN+c>�|Խn�T�/ּ�m�>4S�nvm>�a	�X쥽V_���l:=Y�:;=+P�*��.`k;����B>��UQv�t�=>�7)=��;;��Μ�
VW;�̵��瀽=���kl�>��={1�>Q6�=��K��w���D��$�=���>H��>>2��>K�>������>0��>!�C�&����.>��>�[�=��>���C1>x3�=��>��?=�%4��>�5�������Sý;T�>�k���?>|��=�I�;
-~l>�V���,���ꂽi�߾��>�Ⱥ�{�%>]g�>#^ >���������}�>���K%��K\�<���>v^�<�u(>v���]�^=E�߽9~�>�}�kE��\�'�no�>��>�
-���cɾs��<�/z=#?��8��>�Ǽ=�^�=o*@����>H-�>��N�	���:>����=�Ȗ>�mҽ٨h�2 �>\V�=�T���/�=@}�=��ǽ�-">�>#~���i=�^�=4��>������>QgϾM�
-���ʼ�렾�4
>
�=\T>l�վ�����=������� 2��پuA>J��= ��w+���_'
>�y�>(�
?�	�>h�j>,~��~q`�%>�ʾv�n��;?�(�<h�ɾ0��a��<�:��*�=���#>^����4>.-�>T�>(�~>;�=���>ܼ�>�1?��?6�ɾ�/��=�>�>� �����=�����)���j=U6�F>>l��>A V?�϶��|?��g��6�>�>i�(?�C?���֒��>^%�>�
)?Z&?GN.�P���a��>���}�.?D?]��>H�ܾ���>�U�o{?���㇡�ݳ�>1\�;�;���������=x�>
���;�I��Z�>���.�>�s>��ٽT���թ	�"��>��>*)������<R>��@����>���=���>���>Ya
��V_=^�5=k/ʽ'F�>A�(=4)L>�
��|�>wQ�<����w7?���>^K�=Z"����z�?��>��`?PM%?C��>�;��=3���N>-)��6�>�k�=�P�>O=P?	c�a|
?J
?��#?Z7�>��F�u��:�2>e�=2#�r8�>����ʊ�9D'���-<'��κ>��>�!_���H>������>ޤ�>5��>��4=FU��������=M�>��>U��=.��i����L>q7ν�أ>M��=4��>:n#�:�<ْh����>n�
��k��X%����<W�#�A
�<�R>9t�����)["��@�����>h�=��q�>�:z�]B
-=�±��`��c>�>Ln=<2��(W�=���>�g���2���X��v����
����>홼�&ܾɡ�>�#�o����<>�DE=e,
�(�і���l��Z�´�4���%�����d��w%>aY����'>*�B��+0��v����e����6R�r�,��v">?S�>X͜>2�4?�:?4�??��#�J���3?Ĝ;?�}=?t??
���v�g�<?�I�P+C?��C?p=?�4�yJ
?n����<?9ݾ�꾙�(?��ܾ�]پ�S?�ھ�
���?8��>C5�>+��x��>U��>�M��DϾ����!�(?�#Ҿ(��R�?�ɾ<羚P?o�־�4���D2?���>+$�>�1����>�>S/�w+޾-���&,?���>�:�>��}׾����E�(?p]����ξ�j.?&�۾�ƾ؏!?���>���>?��/����~��[m�>
��>B��>�
�����[���b�-?
+vector_observation����

action_masks����

policy_1/concat_2/concatactionaction_output_shape������?action_output_shape




memory_size





version_number




is_continuous_control




policy_1/add_2/y




policy_1/Sum/reduction_indices




policy_1/add/y




$policy/main_graph_0/hidden_0/BiasAdd
�����?
vector_observation#policy/main_graph_0/hidden_0/kernel

�
!policy/main_graph_0/hidden_0/bias


�
 policy/main_graph_0/hidden_0/Mul2	�����?
$policy/main_graph_0/hidden_0/BiasAddpolicy_1/dense/MatMul
�����?
 policy/main_graph_0/hidden_0/Mulpolicy/dense/kernel

�
<policy_1/dense/MatMul/patch:0


�
policy_1/strided_slice�



�����?
action_maskspolicy_1/Softmax2�����?
policy_1/dense/MatMulpolicy_1/addd�����?policy_1/Softmaxpolicy_1/add/ypolicy_1/Mulf�����?policy_1/addpolicy_1/strided_slicepolicy_1/Sum������?policy_1/Mulpolicy_1/Sum/reduction_indicespolicy_1/truedivg�����?policy_1/Mulpolicy_1/Sumpolicy_1/add_2d�����?policy_1/truedivpolicy_1/add_2/ypolicy_1/Log_12r�����?
policy_1/add_2policy_1/concat_2/concat2�����?
policy_1/Log_1action2�����?
policy_1/concat_2/concat@@@���3�?���3�k��8�
>�:���{i��#���Ld�n�<�B$�=6_��ސ��8�þ�Z=��>���;�/�O�>�����q�=VU�����=�l��e,�-X7������xQ>>�K��$>46���a><9�>�(>�(O>�(>�X�<��=�p��D��m��>���(z����x��;W�}J�;~7���:���G���%�=�>	8�<;��ݾ=��U>;H<8B%����Å2���?���=g0ѽ ������$־ڜ^>w����.��c��؟=Tgx�C��;�o:�z���)�=������eٳ>�
f�9ˡ=���<
+���)��R��=/)�<��z>��H�$5���>�����}y��l�>��[��@�;�Ӵ=�0�=8׾T;>яV�?h���>Y�k=��=�꽕!�>5�=PO�~���L�J=��̾�м.�<�W?�;��[.��h���?k�Q���b>�u=�;��+?�<IE�>��>wz�=���	��s�^>��O>�_>Wo�>t����f����%V>��c<B��>�1c�Q�,�j�<=���>�̭��G�$��<��>0m¾����j�x�q��>�Y�=��>�^1=��Ͼ<�<ξTP��}:�j�>C�
>��=��$>J��>ߖ>��>ג�>�
g>�>������7=�|=�J?Q�=��> �j>
�P>-�l>೘�W^�]�)>��w>��=���*X��|�>4��?�X>�]�ώ�M�N��>�>B��8�)`��/=�G�=���>�2�>����>�>�_�>���<}�n��f>`�!��(Q�qr1�C�6��.�>��
>}���%�Ͼ�Ɖ>�ܘ�N��ӶG<f1��d�?0�K>�꾀"k��Ϭ>���>^�?��'�+�e(��s��c��>7���J����&����>��e�D�(=]����q�rJ�>.y>�(����eϪ>�(>;�,==5�/�>S%>2}>n#n=�C=�i>y���d��=��ν�|�8[)���0�=L��
+$�J�:>E�>��.��!��4�y=+r�>�|���t��}����~����>*%��+>0L��fB>[g��	����>>��=$ݽ=މ?>�z@�y
v�L��>�2h>Bl#>L(��#vZ>�ر���<���=s%�>jx?���=
p�<3ś=�5^���>��=�D->��)>)�˽g����s?H���ε�xc���Ҿ �M?hRӾ�D�S��P*,?�Ծ���f#�K��mC&?�(@?Pꬾ�ാ�x�>Z�?J��>��پk���s�u��&�����>] ��鸉���"���@?-r��Ҝ�x���F}���5�>�T�>��+�����(.?���>U���4n�=�w��`�*�$5>q6�>O�Z�=��=�k�=�L�<&q= �u>d#
+=M���&����ꖾy:;>��²{>6ƀ<:�h�G^�������T���1�>N��[�s�� =�:!>o{>4���A䛾lo�� �]>{�v�`n�c=4���f?�>M���0
m>�X>����Ҷ�<'�>����NV����|>�ꑾh�ɾ4#�悞<'K�>�
���~�=HO�>N8B��Ui�K	�=u��=e`?��+�ǟ;���.�?�)�DP\?�-���@�;-�9V\?N�<��\2��5�ؗ'���e?��W?bl+�\�/��5[?��]?�O����A?L?^?�;E�'�
?n�>{�8��)	?��
?��?�Ik?��>�F6�OI����.@?)~?��>��8���?�-?�$@�=�>�>?)�4��_�+���9?��?�?��?��M?L?�7�h�?�<?8�@

?�?G;�vI&�`<�?�B?d��U��s�??o	�>CI
+?ݪ5��?��?��?���
�~��>�=?wC�f��L�W?

Project/Assets/ML-Agents/Examples/Bouncer/Demos/ExpertBouncer.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/Bouncer/Demos/ExpertBouncer.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using UnityEngine;
-using MLAgents;
-using MLAgents.Sensors;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
+using Unity.MLAgents.Sensors;
 
 public class BouncerAgent : Agent
 {

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

 using UnityEngine;
-using MLAgents;
+using Unity.MLAgents;
 
 public class BouncerTarget : MonoBehaviour
 {

Project/Assets/ML-Agents/Examples/Crawler/Demos/ExpertCrawlerDyn.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/Crawler/Demos/ExpertCrawlerDyn.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

Project/Assets/ML-Agents/Examples/Crawler/Demos/ExpertCrawlerSta.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/Crawler/Demos/ExpertCrawlerSta.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using UnityEngine;
-using MLAgents;
-using MLAgentsExamples;
-using MLAgents.Sensors;
+using Unity.MLAgents;
+using Unity.MLAgentsExamples;
+using Unity.MLAgents.Sensors;
 
 [RequireComponent(typeof(JointDriveController))] // Required to set joint forces
 public class CrawlerAgent : Agent

Project/Assets/ML-Agents/Examples/FoodCollector/Demos/ExpertFood.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/FoodCollector/Demos/ExpertFood.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using UnityEngine;
-using MLAgents;
-using MLAgents.Sensors;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
+using Unity.MLAgents.Sensors;
 
 public class FoodCollectorAgent : Agent
 {

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

 using UnityEngine;
-using MLAgentsExamples;
+using Unity.MLAgentsExamples;
 
 public class FoodCollectorArea : Area
 {

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

 using UnityEngine;
 using UnityEngine.UI;
-using MLAgents;
+using Unity.MLAgents;
 
 public class FoodCollectorSettings : MonoBehaviour
 {
         m_Recorder = Academy.Instance.StatsRecorder;
     }
 
-    private void EnvironmentReset()
+    void EnvironmentReset()
     {
         ClearObjects(GameObject.FindGameObjectsWithTag("food"));
         ClearObjects(GameObject.FindGameObjectsWithTag("badFood"));

Project/Assets/ML-Agents/Examples/GridWorld/Demos/ExpertGrid.demo.meta

 fileFormatVersion: 2
-guid: 3938e0ee1f99e473db8e45d334dfa329
+guid: 0092f2e4aece345aea4730a37eeebf68
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using System;
 using UnityEngine;
 using System.Linq;
-using MLAgents;
-using MLAgents.Sensors;
+using Unity.MLAgents;
-using MLAgents.SideChannels;
 
 public class GridAgent : Agent
 {
 
             if (positionX == 0)
             {
-                actionMasker.SetMask(0, new int[]{ k_Left});
+                actionMasker.SetMask(0, new []{ k_Left});
-                actionMasker.SetMask(0, new int[]{k_Right});
+                actionMasker.SetMask(0, new []{k_Right});
-                actionMasker.SetMask(0, new int[]{k_Down});
+                actionMasker.SetMask(0, new []{k_Down});
-                actionMasker.SetMask(0, new int[]{k_Up});
+                actionMasker.SetMask(0, new []{k_Up});
             }
         }
     }

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

 using System.Collections.Generic;
 using UnityEngine;
 using System.Linq;
-using MLAgents;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
 
 
 public class GridArea : MonoBehaviour
         m_InitialPosition = transform.position;
     }
 
-    private void SetEnvironment()
+    void SetEnvironment()
     {
         transform.position = m_InitialPosition * (m_ResetParams.GetWithDefault("gridSize", 5f) + 1);
         var playersList = new List<int>();

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

 using UnityEngine;
-using MLAgents;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
 
 public class GridSettings : MonoBehaviour
 {

Project/Assets/ML-Agents/Examples/Hallway/Demos/ExpertHallway.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/Hallway/Demos/ExpertHallway.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using System.Collections;
 using UnityEngine;
-using MLAgents;
-using MLAgents.Sensors;
+using Unity.MLAgents;
+using Unity.MLAgents.Sensors;
 
 public class HallwayAgent : Agent
 {

Project/Assets/ML-Agents/Examples/PushBlock/Demos/ExpertPush.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/PushBlock/Demos/ExpertPush.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 
 using System.Collections;
 using UnityEngine;
-using MLAgents;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
 
 public class PushAgentBasic : Agent
 {
     /// </summary>
     Renderer m_GroundRenderer;
 
-    private EnvironmentParameters m_ResetParams;
+    EnvironmentParameters m_ResetParams;
 
     void Awake()
     {
         m_BlockRb.drag = m_ResetParams.GetWithDefault("block_drag", 0.5f);
     }
 
-    private void SetResetParameters()
+    void SetResetParameters()
     {
         SetGroundMaterialFriction();
         SetBlockProperties();

Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using System.Linq;
 using UnityEngine;
 using Random = UnityEngine.Random;
-using MLAgents;
-using MLAgents.Sensors;
+using Unity.MLAgents;
+using Unity.MLAgents.Sensors;
 
 public class PyramidAgent : Agent
 {

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

 using UnityEngine;
-using MLAgentsExamples;
+using Unity.MLAgentsExamples;
 
 public class PyramidArea : Area
 {

Project/Assets/ML-Agents/Examples/Reacher/Demos/ExpertReacher.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/Reacher/Demos/ExpertReacher.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using UnityEngine;
-using MLAgents;
-using MLAgents.Sensors;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
+using Unity.MLAgents.Sensors;
 
 public class ReacherAgent : Agent
 {
     // Frequency of the cosine deviation of the goal along the vertical dimension
     float m_DeviationFreq;
 
-    private EnvironmentParameters m_ResetParams;
+    EnvironmentParameters m_ResetParams;
 
     /// <summary>
     /// Collect the rigidbodies of the reacher in order to resue them for

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

 using UnityEngine;
 
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     public class Area : MonoBehaviour
     {

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

 using UnityEngine;
 
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     public class CameraFollow : MonoBehaviour
     {

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

 using UnityEngine;
 
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     public class FlyCamera : MonoBehaviour
     {

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

 using UnityEngine;
-using MLAgents;
+using Unity.MLAgents;
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     /// <summary>
     /// This class contains logic for locomotion agents with joints which might make contact with the ground.

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

 using System.Collections.Generic;
 using UnityEngine;
 using UnityEngine.Serialization;
-using MLAgents;
+using Unity.MLAgents;
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     /// <summary>
     /// Used to store relevant information for acting and learning for each body part in agent.

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

 using UnityEngine;
 using Unity.Barracuda;
 using System.IO;
-using MLAgents;
-using MLAgents.Policies;
+using Unity.MLAgents;
+using Unity.MLAgents.Policies;
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     /// <summary>
     /// Utility class to allow the NNModel file for an agent to be overriden during inference.
         {
             m_Agent.LazyInitialize();
             var bp = m_Agent.GetComponent<BehaviorParameters>();
-            var name = bp.BehaviorName;
+            var behaviorName = bp.BehaviorName;
-            var nnModel = GetModelForBehaviorName(name);
-            Debug.Log($"Overriding behavior {name} for agent with model {nnModel?.name}");
+            var nnModel = GetModelForBehaviorName(behaviorName);
+            Debug.Log($"Overriding behavior {behaviorName} for agent with model {nnModel?.name}");
-            m_Agent.SetModel($"Override_{name}", nnModel);
+            m_Agent.SetModel($"Override_{behaviorName}", nnModel);
 
         }
     }

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

 using System.Linq;
 using UnityEngine;
 
-namespace MLAgents
+namespace Unity.MLAgents
 {
     /// <summary>
     /// Monitor is used to display information about the Agent within the Unity
             s_TransformCamera = new Dictionary<Transform, Camera>();
         }
 
-        /// <inheritdoc/>
         void OnGUI()
         {
             if (!s_Initialized)

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

 using UnityEngine;
-using MLAgents;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     /// <summary>
     /// A helper class for the ML-Agents example scenes to override various

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

-using MLAgents.Sensors;
+using Unity.MLAgents.Sensors;
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     /// <summary>
     /// A simple sensor that provides a number default implementations.

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

 using UnityEngine;
 
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
 {
     /// <summary>
     /// This class contains logic for locomotion agents with joints which might make contact with a target.

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

 using System;
 using UnityEngine;
-using MLAgents;
-using MLAgents.Policies;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
+using Unity.MLAgents.Policies;
 
 public class AgentSoccer : Agent
 {
     float m_ForwardSpeed;
 
     [HideInInspector]
-    public float timePenalty = 0;
+    public float timePenalty;
 
     [HideInInspector]
     public Rigidbody agentRb;
 
-    private EnvironmentParameters m_ResetParams;
+    EnvironmentParameters m_ResetParams;
 
     public override void Initialize()
     {

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

 using System.Collections;
 using System.Collections.Generic;
-using MLAgents;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
 using UnityEngine;
 using UnityEngine.Serialization;
 
     [HideInInspector]
     public bool canResetBall;
 
-    private EnvironmentParameters m_ResetParams;
+    EnvironmentParameters m_ResetParams;
 
     void Awake()
     {

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

 using UnityEngine;
 using UnityEngine.SceneManagement;
 
-namespace MLAgentsExamples
+namespace Unity.MLAgentsExamples
-        private const string k_SceneCommandLineFlag = "--mlagents-scene-name";
+        const string k_SceneCommandLineFlag = "--mlagents-scene-name";
-            
+
             // Check for the CLI '--scene-name' flag.  This will be used if
             // no scene environment variable is found.
             var args = Environment.GetCommandLineArgs();
             {
                 sceneName = sceneEnvironmentVariable;
             }
-            
+
             SwitchScene(sceneName);
         }
 

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

 using UnityEngine;
-using MLAgents;
-using MLAgents.Sensors;
+using Unity.MLAgents;
+using Unity.MLAgents.Sensors;
 
 public class TemplateAgent : Agent
 {

Project/Assets/ML-Agents/Examples/Tennis/Demos/ExpertTennis.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/Tennis/Demos/ExpertTennis.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using UnityEngine;
 using UnityEngine.UI;
-using MLAgents;
-using MLAgents.Sensors;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
+using Unity.MLAgents.Sensors;
 
 public class TennisAgent : Agent
 {

Project/Assets/ML-Agents/Examples/Walker/Demos/ExpertWalker.demo.meta

   fileIDToRecycleName:
     11400000: Assets/ML-Agents/Examples/Walker/Demos/ExpertWalker.demo
   externalObjects: {}
-  userData: ' (MLAgents.Demonstrations.DemonstrationSummary)'
+  userData: ' (Unity.MLAgents.Demonstrations.DemonstrationSummary)'
   assetBundleName: 
   assetBundleVariant: 
   script: {fileID: 11500000, guid: 7bd65ce151aaa4a41a45312543c56be1, type: 3}

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

 using UnityEngine;
-using MLAgents;
-using MLAgentsExamples;
-using MLAgents.Sensors;
-using MLAgents.SideChannels;
+using Unity.MLAgents;
+using Unity.MLAgentsExamples;
+using Unity.MLAgents.Sensors;
 
 public class WalkerAgent : Agent
 {

Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs

 
 using System.Collections;
 using UnityEngine;
-using MLAgents;
+using Unity.MLAgents;
-using MLAgents.Sensors;
-using MLAgents.SideChannels;
+using Unity.MLAgents.Sensors;
 
 public class WallJumpAgent : Agent
 {

Project/Assets/ML-Agents/Examples/Worm/Scripts/WormAgent.cs

-using System.Collections;
-using MLAgents;
-using MLAgentsExamples;
-using MLAgents.Sensors;
+using Unity.MLAgents;
+using Unity.MLAgentsExamples;
+using Unity.MLAgents.Sensors;
 
 [RequireComponent(typeof(JointDriveController))] // Required to set joint forces
 public class WormAgent : Agent
     public bool respawnTargetWhenTouched;
     public float targetSpawnRadius;
 
-    [Header("Body Parts")] [Space(10)] 
+    [Header("Body Parts")] [Space(10)]
-    [Header("Joint Settings")] [Space(10)] 
+    [Header("Joint Settings")] [Space(10)]
     JointDriveController m_JdController;
     Vector3 m_DirToTarget;
     float m_MovingTowardsDot;
         m_JdController.SetupBodyPart(bodySegment1);
         m_JdController.SetupBodyPart(bodySegment2);
         m_JdController.SetupBodyPart(bodySegment3);
-        
+
         //We only want the head to detect the target
         //So we need to remove TargetContact from everything else
         //This is a temp fix till we can redesign
     }
 
-    
+
     //Get Joint Rotation Relative to the Connected Rigidbody
     //We want to collect this info because it is the actual rotation, not the "target rotation"
     public Quaternion GetJointRotation(ConfigurableJoint joint)
             sensor.AddObservation(bp.currentStrength / m_JdController.maxJointForceLimit);
         }
     }
-    
+
     public override void CollectObservations(VectorSensor sensor)
     {
         m_JdController.GetCurrentJointForces();

README.md

-<img src="docs/images/unity-wide.png" align="middle" width="3000"/>
+<img src="docs/images/image-banner.png" align="middle" width="3000"/>
+
+# Unity ML-Agents Toolkit
-<img src="docs/images/image-banner.png" align="middle" width="3000"/>
+[![docs badge](https://img.shields.io/badge/docs-reference-blue.svg)](https://github.com/Unity-Technologies/ml-agents/tree/release_1_docs/docs/)
-# Unity ML-Agents Toolkit (Beta)
-[![docs badge](https://img.shields.io/badge/docs-reference-blue.svg)](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/)
 [![license badge](https://img.shields.io/badge/license-Apache--2.0-green.svg)](LICENSE)
 
 ([latest release](https://github.com/Unity-Technologies/ml-agents/releases/tag/latest_release))
-Unity plugin that enables games and simulations to serve as environments for
+project that enables games and simulations to serve as environments for
 training intelligent agents. Agents can be trained using reinforcement learning,
 imitation learning, neuroevolution, or other machine learning methods through a
 simple-to-use Python API. We also provide implementations (based on TensorFlow)
 
 ## Features
 
-* Unity environment control from Python
-* 15+ sample Unity environments
-* Two deep reinforcement learning algorithms,
-[Proximal Policy Optimization](docs/Training-PPO.md)
- (PPO) and [Soft Actor-Critic](docs/Training-SAC.md)
- (SAC)
-* Support for multiple environment configurations and training scenarios
-* Self-play mechanism for training agents in adversarial scenarios
-* Train memory-enhanced agents using deep reinforcement learning
-* Easily definable Curriculum Learning and Generalization scenarios
-* Built-in support for [Imitation Learning](docs/Training-Imitation-Learning.md) through Behavioral Cloning or Generative Adversarial Imitation Learning
-* Flexible agent control with On Demand Decision Making
-* Visualizing network outputs within the environment
-* Wrap learning environments as a gym
-* Utilizes the Unity Inference Engine
-* Train using concurrent Unity environment instances
+- 15+ [example Unity environments](docs/Learning-Environment-Examples.md)
+- Support for multiple environment configurations and training scenarios
+- Flexible Unity SDK that can be integrated into your game or custom Unity scene
+- Training using two deep reinforcement learning algorithms, Proximal Policy
+  Optimization (PPO) and Soft Actor-Critic (SAC)
+- Built-in support for Imitation Learning through Behavioral Cloning or
+  Generative Adversarial Imitation Learning
+- Self-play mechanism for training agents in adversarial scenarios
+- Easily definable Curriculum Learning scenarios for complex tasks
+- Train robust agents using environment randomization
+- Flexible agent control with On Demand Decision Making
+- Train using multiple concurrent Unity environment instances
+- Utilizes the [Unity Inference Engine](docs/Unity-Inference-Engine.md) to
+  provide native cross-platform support
+- Unity environment [control from Python](docs/Python-API.md)
+- Wrap Unity learning environments as a [gym](gym-unity/README.md)
+
+See our [ML-Agents Overview](docs/ML-Agents-Overview.md) page for detailed
+descriptions of all these features.
-**Our latest, stable release is 0.15.1. Click
-[here](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Readme.md) to
+
+**Our latest, stable release is `Release 1`. Click [here](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
 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).
-
-| **0.15.1** | **March 30, 2020** | **[source](https://github.com/Unity-Technologies/ml-agents/tree/0.15.1)** | **[docs](https://github.com/Unity-Technologies/ml-agents/tree/0.15.1/docs/Readme.md)** | **[download](https://github.com/Unity-Technologies/ml-agents/archive/0.15.1.zip)** |
+| **Release 1** | **April 30, 2020** | **[source](https://github.com/Unity-Technologies/ml-agents/tree/release_1)** | **[docs](https://github.com/Unity-Technologies/ml-agents/tree/release_1/docs/Readme.md)** | **[download](https://github.com/Unity-Technologies/ml-agents/archive/release_1.zip)** |
+| **0.15.1** | March 30, 2020 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.15.1) | [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.15.1/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.15.1.zip) |
 | **0.15.0** | March 18, 2020 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.15.0) | [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.15.0/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.15.0.zip) |
 | **0.14.1** | February 26, 2020 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.14.1) | [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.14.1/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.14.1.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) |
 | **0.12.0** | 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) |
-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 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.
+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/)
-* Overviewing reinforcement learning concepts
+
+- (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/)
+- Overviewing reinforcement learning concepts
-In addition to our own documentation, here are some additional, relevant articles:
+In addition to our own documentation, here are some additional, relevant
+articles:
-* [A Game Developer Learns Machine Learning](https://mikecann.co.uk/machine-learning/a-game-developer-learns-machine-learning-intent/)
-* [Explore Unity Technologies ML-Agents Exclusively on Intel Architecture](https://software.intel.com/en-us/articles/explore-unity-technologies-ml-agents-exclusively-on-intel-architecture)
-* [ML-Agents Penguins tutorial](https://learn.unity.com/project/ml-agents-penguins)
+- [A Game Developer Learns Machine Learning](https://mikecann.co.uk/machine-learning/a-game-developer-learns-machine-learning-intent/)
+- [Explore Unity Technologies ML-Agents Exclusively on Intel Architecture](https://software.intel.com/en-us/articles/explore-unity-technologies-ml-agents-exclusively-on-intel-architecture)
+- [ML-Agents Penguins tutorial](https://learn.unity.com/project/ml-agents-penguins)
 
 ## Community and Feedback
 
 
 For problems with the installation and setup of the the ML-Agents Toolkit, or
 discussions about how to best setup or train your agents, please create a new
-thread on the [Unity ML-Agents forum](https://forum.unity.com/forums/ml-agents.453/)
-and make sure to include as much detail as possible.
-If you run into any other problems using the ML-Agents Toolkit, or have a specific
-feature requests, please [submit a GitHub issue](https://github.com/Unity-Technologies/ml-agents/issues).
+thread on the
+[Unity ML-Agents forum](https://forum.unity.com/forums/ml-agents.453/) and make
+sure to include as much detail as possible. If you run into any other problems
+using the ML-Agents Toolkit, or have a specific feature requests, please
+[submit a GitHub issue](https://github.com/Unity-Technologies/ml-agents/issues).
-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
+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
-For any other questions or feedback, connect directly with the ML-Agents
-team at ml-agents@unity3d.com.
-
+For any other questions or feedback, connect directly with the ML-Agents team at
+ml-agents@unity3d.com.
 
 ## License
 

SURVEY.md

 # Unity ML-Agents Toolkit Survey
 
-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.
+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.
-[Fill out the survey](https://goo.gl/forms/qFMYSYr5TlINvG6f1)
+[Fill out the survey](https://goo.gl/forms/qFMYSYr5TlINvG6f1)

com.unity.ml-agents/CHANGELOG.md

 ### Major Changes
 #### com.unity.ml-agents (C#)
 #### ml-agents / ml-agents-envs / gym-unity (Python)
+- `max_step` in the `TerminalStep` and `TerminalSteps` objects was renamed `interrupted`.
+- Curriculum and Parameter Randomization configurations have been merged
+  into the main training configuration file. Note that this means training
+  configuration files are now environment-specific. (#3791)
+- Training artifacts (trained models, summaries) are now found in the `results/`
+  directory. (#3829)
+- Unity Player logs are now written out to the results directory. (#3877)
+- Run configuration YAML files are written out to the results directory at the end of the run. (#3815)
-## [1.0.0-preview] - 2020-05-06
+## [1.0.0-preview] - 2020-04-30
-- Added new 3-joint Worm ragdoll environment. (#3798)
-- The `--load` and `--train` command-line flags have been deprecated. Training
-  now happens by default, and use `--resume` to resume training instead. (#3705)
-- The Jupyter notebooks have been removed from the repository.
-- Removed the multi-agent gym option from the gym wrapper. For multi-agent
-  scenarios, use the [Low Level Python API](../docs/Python-API.md).
-- The low level Python API has changed. You can look at the document
-  [Low Level Python API documentation](../docs/Python-API.md) for more
-  information. If you use `mlagents-learn` for training, this should be a
-  transparent change.
-- 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
+
+#### com.unity.ml-agents (C#)
+
+- The `MLAgents` C# namespace was renamed to `Unity.MLAgents`, and other nested
+  namespaces were similarly renamed. (#3843)
+- The offset logic was removed from DecisionRequester. (#3716)
+- The signature of `Agent.Heuristic()` was changed to take a float array as a
-  source of error where users would return arrays of the wrong size.
+  source of error where users would return arrays of the wrong size. (#3765)
-  communication between Unity and the Python process.
+  communication between Unity and the Python process. (#3760)
-  `AgentAction` and `AgentReset` have been removed.
-- The GhostTrainer has been extended to support asymmetric games and the
-  asymmetric example environment Strikers Vs. Goalie has been added.
-- The SideChannel API has changed (#3833, #3660) :
+  `AgentAction` and `AgentReset` have been removed. (#3770)
+- The SideChannel API has changed:
-  channels.
-  - `EnvironmentParameters` replaces the default `FloatProperties`.
-  You can access the `EnvironmentParameters` with
-  `Academy.Instance.EnvironmentParameters` on C# and create an
-  `EnvironmentParametersChannel` on Python
+    channels. (#3807)
+  - `Academy.FloatProperties` was replaced by `Academy.EnvironmentParameters`.
+    See the [Migration Guide](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Migrating.md)
+    for more details on upgrading. (#3807)
-  which is used when trying to read more data than the message contains.
+    which is used when trying to read more data than the message contains. (#3751)
-  (and other python StatsWriters). To do this from your code, use
-  `Academy.Instance.StatsRecorder.Add(key, value)`(#3660)
-- CameraSensorComponent.m_Grayscale and RenderTextureSensorComponent.m_Grayscale
-  were changed from `public` to `private` (#3808).
-- The `UnityEnv` class from the `gym-unity` package was renamed
-  `UnityToGymWrapper` and no longer creates the `UnityEnvironment`.
-  Instead, the `UnityEnvironment` must be passed as input to the
-  constructor of `UnityToGymWrapper`
+    (and other python StatsWriters). To do this from your code, use
+    `Academy.Instance.StatsRecorder.Add(key, value)`. (#3660)
+- `CameraSensorComponent.m_Grayscale` and
+  `RenderTextureSensorComponent.m_Grayscale` were changed from `public` to
+  `private`. These can still be accessed via their corresponding properties.
+  (#3808)
-- Update Barracuda to 0.7.0-preview which has breaking namespace and assembly name changes.
+- `WriteAdapter` was renamed to `ObservationWriter`. If you have a custom
+  `ISensor` implementation, you will need to change the signature of its
+  `Write()` method. (#3834)
+- The Barracuda dependency was upgraded to 0.7.0-preview (which has breaking
+  namespace and assembly name changes). (#3875)
+
+#### ml-agents / ml-agents-envs / gym-unity (Python)
+
+- The `--load` and `--train` command-line flags have been deprecated. Training
+  now happens by default, and use `--resume` to resume training instead of
+  `--load`. (#3705)
+- The Jupyter notebooks have been removed from the repository. (#3704)
+- The multi-agent gym option was removed from the gym wrapper. For multi-agent
+  scenarios, use the [Low Level Python API](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Python-API.md). (#3681)
+- The low level Python API has changed. You can look at the document
+  [Low Level Python API](https://github.com/Unity-Technologies/ml-agents/blob/master/docs/Python-API.md)
+  documentation for more information. If you use `mlagents-learn` for training, this should be a
+  transparent change. (#3681)
+- Added ability to start training (initialize model weights) from a previous run
+  ID. (#3710)
+- The GhostTrainer has been extended to support asymmetric games and the
+  asymmetric example environment Strikers Vs. Goalie has been added. (#3653)
+- The `UnityEnv` class from the `gym-unity` package was renamed
+  `UnityToGymWrapper` and no longer creates the `UnityEnvironment`. Instead, the
+  `UnityEnvironment` must be passed as input to the constructor of
+  `UnityToGymWrapper` (#3812)
+#### com.unity.ml-agents (C#)
+
+- Added new 3-joint Worm ragdoll environment. (#3798)
+- `StackingSensor` was changed from `internal` visibility to `public`. (#3701)
+- The internal event `Academy.AgentSetStatus` was renamed to
+  `Academy.AgentPreStep` and made public. (#3716)
+- Academy.InferenceSeed property was added. This is used to initialize the
+  random number generator in ModelRunner, and is incremented for each
+  ModelRunner. (#3823)
+- `Agent.GetObservations()` was added, which returns a read-only view of the
+  observations added in `CollectObservations()`. (#3825)
+- `UnityRLCapabilities` was added to help inform users when RL features are
+  mismatched between C# and Python packages. (#3831)
+
+#### ml-agents / ml-agents-envs / gym-unity (Python)
+
+  (#3646)
-  package version numbers.
+  package version numbers. (#3758)
-  environment port) will be used.
-- Fixed an issue where exceptions from environments provided a returncode of 0.
-  (#3680)
+  environment port) will be used. (#3673)
-- `StackingSensor` was changed from `internal` visibility to `public`
-- Academy.InferenceSeed property was added. This is used to initialize the
-  random number generator in ModelRunner, and is incremented for each ModelRunner. (#3823)
-- Added `Agent.GetObservations(), which returns a read-only view of the observations
-  added in `CollectObservations()`. (#3825)
-- Model updates can now happen asynchronously with environment steps for better performance. (#3690)
-- `num_updates` and `train_interval` for SAC were replaced with `steps_per_update`. (#3690)
-- `WriteAdapter` was renamed to `ObservationWriter`. If you have a custom `ISensor` implementation,
-you will need to change the signature of its `Write()` method. (#3834)
-- The maximum compatible version of tensorflow was changed to allow tensorflow 2.1 and 2.2. This
-will allow use with python 3.8 using tensorflow 2.2.0rc3.
-- `UnityRLCapabilities` was added to help inform users when RL features are mismatched between C# and Python packages. (#3831)
+- Model updates can now happen asynchronously with environment steps for better
+  performance. (#3690)
+- `num_updates` and `train_interval` for SAC were replaced with
+  `steps_per_update`. (#3690)
+- The maximum compatible version of tensorflow was changed to allow tensorflow
+  2.1 and 2.2. This will allow use with python 3.8 using tensorflow 2.2.0rc3.
+  (#3830)
+- `mlagents-learn` will no longer set the width and height of the executable
+  window to 84x84 when no width nor height arguments are given. (#3867)
- - Fixed a display bug when viewing Demonstration files in the inspector. The
-   shapes of the observations in the file now display correctly. (#3771)
+#### com.unity.ml-agents (C#)
+
+- Fixed a display bug when viewing Demonstration files in the inspector. The
+  shapes of the observations in the file now display correctly. (#3771)
+
+#### ml-agents / ml-agents-envs / gym-unity (Python)
+
+- Fixed an issue where exceptions from environments provided a return code of 0.
+  (#3680)
+- Self-Play team changes will now trigger a full environment reset. This
+  prevents trajectories in progress during a team change from getting into the
+  buffer. (#3870)
 
 ## [0.15.1-preview] - 2020-03-30
 

com.unity.ml-agents/CONTRIBUTING.md

 
 ## Communication
 
-First, please read through our [code of conduct](https://github.com/Unity-Technologies/ml-agents/blob/master/CODE_OF_CONDUCT.md), as we
-expect all our contributors to follow it.
+First, please read through our
+[code of conduct](https://github.com/Unity-Technologies/ml-agents/blob/master/CODE_OF_CONDUCT.md),
+as we expect all our contributors to follow it.
-[Issues page](https://github.com/Unity-Technologies/ml-agents/issues)
-and briefly outlining the changes you plan to make. This will enable us to
-provide some context that may be helpful for you. This could range from advice
-and feedback on how to optimally perform your changes or reasons for not doing
-it.
+[Issues page](https://github.com/Unity-Technologies/ml-agents/issues) and
+briefly outlining the changes you plan to make. This will enable us to provide
+some context that may be helpful for you. This could range from advice and
+feedback on how to optimally perform your changes or reasons for not doing it.
-Lastly, if you're looking for input on what to contribute, feel free to
-reach out to us directly at ml-agents@unity3d.com and/or browse the GitHub
-issues with the `contributions welcome` label.
+Lastly, if you're looking for input on what to contribute, feel free to reach
+out to us directly at ml-agents@unity3d.com and/or browse the GitHub issues with
+the `contributions welcome` label.
-The master branch corresponds to the most recent version of the project.
-Note that this may be newer that the [latest release](https://github.com/Unity-Technologies/ml-agents/releases/tag/latest_release).
-When contributing to the project, please make sure that your Pull Request (PR) contains the following:
+The master branch corresponds to the most recent version of the project. Note
+that this may be newer that the
+[latest release](https://github.com/Unity-Technologies/ml-agents/releases/tag/latest_release).
+
+When contributing to the project, please make sure that your Pull Request (PR)
+contains the following:
-* Detailed description of the changes performed
-* Corresponding changes to documentation, unit tests and sample environments (if
+- Detailed description of the changes performed
+- Corresponding changes to documentation, unit tests and sample environments (if
-* Summary of the tests performed to validate your changes
-* Issue numbers that the PR resolves (if any)
+- Summary of the tests performed to validate your changes
+- Issue numbers that the PR resolves (if any)
-examples, as long as they are small, simple, demonstrate a unique feature of
-the platform, and provide a unique non-trivial challenge to modern
-machine learning algorithms. Feel free to submit these environments with a
-PR explaining the nature of the environment and task.
+examples, as long as they are small, simple, demonstrate a unique feature of the
+platform, and provide a unique non-trivial challenge to modern machine learning
+algorithms. Feel free to submit these environments with a PR explaining the
+nature of the environment and task.
-Several static checks are run on the codebase using the [pre-commit framework](https://pre-commit.com/) during CI. To execute the same checks locally, install `pre-commit` and run `pre-commit run --all-files`. Some hooks (for example, `black`) will output the corrected version of the code; others (like `mypy`) may require more effort to fix.
+Several static checks are run on the codebase using the
+[pre-commit framework](https://pre-commit.com/) during CI. To execute the same
+checks locally, install `pre-commit` and run `pre-commit run --all-files`. Some
+hooks (for example, `black`) will output the corrected version of the code;
+others (like `mypy`) may require more effort to fix.
-All python code should be formatted with [`black`](https://github.com/ambv/black). Style and formatting for C# may be enforced later.
+
+All python code should be formatted with
+[`black`](https://github.com/ambv/black). Style and formatting for C# may be
+enforced later.