fix release_1 references (#4001)

.pre-commit-config.yaml

         files: "gym-unity/.*"
         args: [--ignore-missing-imports, --disallow-incomplete-defs]
 
+-   repo: https://gitlab.com/pycqa/flake8
+    rev: 3.8.1
+    hooks:
+    -   id: flake8
+        exclude: >
+            (?x)^(
+                .*_pb2.py|
+                .*_pb2_grpc.py
+            )$
+        # flake8-tidy-imports is used for banned-modules, not actually tidying
+        additional_dependencies: [flake8-comprehensions==3.2.2, flake8-tidy-imports==4.1.0, flake8-bugbear==20.1.4]
+
-    rev: v2.4.0
+    rev: v2.5.0
     hooks:
     -   id: mixed-line-ending
         exclude: >
                 .*.meta
             )$
         args: [--fix=lf]
-    -   id: flake8
-        exclude: >
-            (?x)^(
-                .*_pb2.py|
-                .*_pb2_grpc.py
-            )$
-        # flake8-tidy-imports is used for banned-modules, not actually tidying
-        additional_dependencies: [flake8-comprehensions==3.1.4, flake8-tidy-imports==4.0.0, flake8-bugbear==20.1.2]
+
     -   id: trailing-whitespace
         name: trailing-whitespace-markdown
         types: [markdown]

gym-unity/gym_unity/__init__.py

 # Version of the library that will be used to upload to pypi
-__version__ = "0.16.0"
+__version__ = "0.16.1"
-__release_tag__ = "release_1"
+__release_tag__ = "release_2"

gym-unity/gym_unity/envs/__init__.py

             self._env.step()
 
         self.visual_obs = None
-        self._n_agents = -1
 
         # Save the step result from the last time all Agents requested decisions.
         self._previous_decision_step: DecisionSteps = None
 
         self._env.step()
         decision_step, terminal_step = self._env.get_steps(self.name)
+        self._check_agents(max(len(decision_step), len(terminal_step)))
         if len(terminal_step) != 0:
             # The agent is done
             self.game_over = True
         logger.warning("Could not seed environment %s", self.name)
         return
 
-    def _check_agents(self, n_agents: int) -> None:
-        if self._n_agents > 1:
+    @staticmethod
+    def _check_agents(n_agents: int) -> None:
+        if n_agents > 1:
-                "There can only be one Agent in the environment but {n_agents} were detected."
+                f"There can only be one Agent in the environment but {n_agents} were detected."
             )
 
     @property
     @property
     def observation_space(self):
         return self._observation_space
-
-    @property
-    def number_agents(self):
-        return self._n_agents
 
 
 class ActionFlattener:

ml-agents-envs/mlagents_envs/__init__.py

 # Version of the library that will be used to upload to pypi
-__version__ = "0.16.0"
+__version__ = "0.16.1"
-__release_tag__ = "release_1"
+__release_tag__ = "release_2"

ml-agents-envs/mlagents_envs/environment.py

         expected_shape = (len(self._env_state[behavior_name][0]), spec.action_size)
         if action.shape != expected_shape:
             raise UnityActionException(
-                "The behavior {0} needs an input of dimension {1} but received input of dimension {2}".format(
-                    behavior_name, expected_shape, action.shape
-                )
+                "The behavior {0} needs an input of dimension {1} for "
+                "(<number of agents>, <action size>) but received input of "
+                "dimension {2}".format(behavior_name, expected_shape, action.shape)
             )
         if action.dtype != expected_type:
             action = action.astype(expected_type)

ml-agents/tests/yamato/check_coverage_percent.py

         # Rather than try to parse the XML, just look for a line of the form
         # <Linecoverage>73.9</Linecoverage>
         lines = f.readlines()
-        for l in lines:
-            if "Linecoverage" in l:
-                pct = l.replace("<Linecoverage>", "").replace("</Linecoverage>", "")
+        for line in lines:
+            if "Linecoverage" in line:
+                pct = line.replace("<Linecoverage>", "").replace("</Linecoverage>", "")
                 pct = float(pct)
                 if pct < min_percentage:
                     print(

ml-agents/tests/yamato/yamato_utils.py

     subprocess.check_call("git reset HEAD .", shell=True)
     subprocess.check_call("git checkout -- .", shell=True)
     # Ensure the cache isn't polluted with old compiled assemblies.
-    subprocess.check_call(f"rm -rf Project/Library", shell=True)
+    subprocess.check_call("rm -rf Project/Library", shell=True)
 
 
 def override_config_file(src_path, dest_path, **kwargs):

ml-agents/mlagents/trainers/__init__.py

 # Version of the library that will be used to upload to pypi
-__version__ = "0.16.0"
+__version__ = "0.16.1"
-__release_tag__ = "release_1"
+__release_tag__ = "release_2"

ml-agents/mlagents/trainers/ppo/trainer.py

             self.update_buffer.shuffle(sequence_length=self.policy.sequence_length)
             buffer = self.update_buffer
             max_num_batch = buffer_length // batch_size
-            for l in range(0, max_num_batch * batch_size, batch_size):
+            for i in range(0, max_num_batch * batch_size, batch_size):
-                    buffer.make_mini_batch(l, l + batch_size), n_sequences
+                    buffer.make_mini_batch(i, i + batch_size), n_sequences
                 )
                 for stat_name, value in update_stats.items():
                     batch_update_stats[stat_name].append(value)

ml-agents/mlagents/trainers/subprocess_env_manager.py

         return self.env_workers[0].recv().payload
 
     def close(self) -> None:
-        logger.debug(f"SubprocessEnvManager closing.")
+        logger.debug("SubprocessEnvManager closing.")
         self.step_queue.close()
         self.step_queue.join_thread()
         for env_worker in self.env_workers:

ml-agents/mlagents/trainers/policy/tf_policy.py

                     )
                 )
             if reset_global_steps:
+                self._set_step(0)
                 logger.info(
                     "Starting training from step 0 and saving to {}.".format(
                         self.model_path

ml-agents/mlagents/trainers/tests/test_nn_policy.py

     trainer_params["model_path"] = path1
     policy = create_policy_mock(trainer_params)
     policy.initialize_or_load()
+    policy._set_step(2000)
     policy.save_model(2000)
 
     assert len(os.listdir(tmp_path)) > 0
     policy2.initialize_or_load()
     _compare_two_policies(policy, policy2)
+    assert policy2.get_current_step() == 2000
 
     # Try initialize from path 1
     trainer_params["model_path"] = path2
 
     _compare_two_policies(policy2, policy3)
+    # Assert that the steps are 0.
+    assert policy3.get_current_step() == 0
 
 
 def _compare_two_policies(policy1: NNPolicy, policy2: NNPolicy) -> None:

README.md

 
 # Unity ML-Agents Toolkit
 
-[![docs badge](https://img.shields.io/badge/docs-reference-blue.svg)](https://github.com/Unity-Technologies/ml-agents/tree/release_1_docs/docs/)
+[![docs badge](https://img.shields.io/badge/docs-reference-blue.svg)](https://github.com/Unity-Technologies/ml-agents/tree/release_2_docs/docs/)
 
 [![license badge](https://img.shields.io/badge/license-Apache--2.0-green.svg)](LICENSE)
 
 
 ## Releases & Documentation
 
-**Our latest, stable release is `Release 1`. Click [here](docs/Readme.md) to
-get started with the latest release of ML-Agents.**
+**Our latest, stable release is `Release 2`. Click
+[here](https://github.com/Unity-Technologies/ml-agents/tree/release_2_docs/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).
+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 [Versioning page](docs/Versioning.md) overviews how we manage our GitHub
+  releases and the versioning process for each of the ML-Agents components.
+- The [Releases page](https://github.com/Unity-Technologies/ml-agents/releases)
+  contains details of the changes between releases.
+- The [Migration page](docs/Migrating.md) contains details on how to upgrade
+  from earlier releases of the ML-Agents Toolkit.
+- The **Documentation** 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.
-| **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)** |
+| **Release 2** | **May 19, 2020** | **[source](https://github.com/Unity-Technologies/ml-agents/tree/release_2)** | **[docs](https://github.com/Unity-Technologies/ml-agents/tree/release_2/docs/Readme.md)** | **[download](https://github.com/Unity-Technologies/ml-agents/archive/release_2.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) |
-| **0.12.1** | 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) |
-
 ## Citation
 
 If you are a researcher interested in a discussion of Unity as an AI platform,
 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.
+Juliani, A., Berges, V., Teng, E., Cohen, A., Harper, J., Elion, C., Goy, C.,
+Gao, Y., Henry, H., Mattar, M., Lange, D. (2020). Unity: A General Platform for
+Intelligent Agents. _arXiv preprint
+[arXiv:1809.02627](https://arxiv.org/abs/1809.02627)._
+https://github.com/Unity-Technologies/ml-agents.
+- (May 12, 2020)
+  [Announcing ML-Agents Unity Package v1.0!](https://blogs.unity3d.com/2020/05/12/announcing-ml-agents-unity-package-v1-0/)
 - (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)

utils/validate_versions.py

 
 def extract_version_string(filename):
     with open(filename) as f:
-        for l in f.readlines():
-            if l.startswith(VERSION_LINE_START):
-                return l.replace(VERSION_LINE_START, "").strip()
+        for line in f.readlines():
+            if line.startswith(VERSION_LINE_START):
+                return line.replace(VERSION_LINE_START, "").strip()
     return None
 
 
         f.writelines(lines)
 
 
+def print_release_tag_commands(
+    python_version: str, csharp_version: str, release_tag: str
+):
+    python_tag = f"python-packages_{python_version}"
+    csharp_tag = f"com.unity.ml-agents_{csharp_version}"
+    docs_tag = f"{release_tag}_docs"
+    print(
+        f"""
+###
+Use these commands to create the tags after the release:
+###
+git checkout {release_tag}
+git tag -f latest_release
+git push -f origin latest_release
+git tag -f {docs_tag}
+git push -f origin {docs_tag}
+git tag {python_tag}
+git push -f origin {python_tag}
+git tag {csharp_tag}
+git push -f origin {csharp_tag}
+"""
+    )
+
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("--python-version", default=None)
         if args.csharp_version:
             print(f"Updating C# package to version {args.csharp_version}")
         set_version(args.python_version, args.csharp_version, args.release_tag)
+        if args.release_tag is not None:
+            print_release_tag_commands(
+                args.python_version, args.csharp_version, args.release_tag
+            )
     else:
         ok = check_versions()
         return_code = 0 if ok else 1

utils/make_readme_table.py

     ReleaseInfo.from_simple_tag("0.15.0", "March 18, 2020"),
     ReleaseInfo.from_simple_tag("0.15.1", "March 30, 2020"),
     ReleaseInfo("release_1", "1.0.0", "0.16.0", "April 30, 2020"),
+    ReleaseInfo("release_2", "1.0.1", "0.16.1", "May 19, 2020"),
 ]
 
 MAX_DAYS = 150  # do not print releases older than this many days

com.unity.ml-agents/package.json

 {
   "name": "com.unity.ml-agents",
   "displayName": "ML Agents",
-  "version": "1.0.0-preview",
+  "version": "1.0.2-preview",
-    "com.unity.barracuda": "0.7.0-preview"
+    "com.unity.barracuda": "0.7.1-preview"
-}
+}

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

         static void DrawContinuousVectorAction(Rect position, SerializedProperty property)
         {
             var vecActionSize = property.FindPropertyRelative(k_ActionSizePropName);
-            vecActionSize.arraySize = 1;
+
+            // This check is here due to:
+            // https://fogbugz.unity3d.com/f/cases/1246524/
+            // If this case has been resolved, please remove this if condition.
+            if (vecActionSize.arraySize != 1)
+            {
+                vecActionSize.arraySize = 1;
+            }
             var continuousActionSize =
                 vecActionSize.GetArrayElementAtIndex(0);
             EditorGUI.PropertyField(
         static void DrawDiscreteVectorAction(Rect position, SerializedProperty property)
         {
             var vecActionSize = property.FindPropertyRelative(k_ActionSizePropName);
-            vecActionSize.arraySize = EditorGUI.IntField(
+            var newSize = EditorGUI.IntField(
+
+            // This check is here due to:
+            // https://fogbugz.unity3d.com/f/cases/1246524/
+            // If this case has been resolved, please remove this if condition.
+            if (newSize != vecActionSize.arraySize)
+            {
+                vecActionSize.arraySize = newSize;
+            }
+
             position.y += k_LineHeight;
             position.x += 20;
             position.width -= 20;

com.unity.ml-agents/Tests/Editor/PublicAPI/Unity.ML-Agents.Editor.Tests.PublicAPI.asmdef

     "references": [
         "Unity.ML-Agents.Editor",
         "Unity.ML-Agents",
-        "Barracuda",
+        "Unity.Barracuda",
         "Unity.ML-Agents.CommunicatorObjects"
     ],
     "optionalUnityReferences": [

com.unity.ml-agents/Tests/Editor/Sensor/SensorShapeValidatorTests.cs

             validator.ValidateSensors(sensorList1);
 
             var sensorList2 = new List<ISensor>() { new DummySensor(1), new DummySensor(2, 3), new DummySensor(4, 5, 7) };
-            LogAssert.Expect(LogType.Assert, "Sensor sizes much match.");
+            LogAssert.Expect(LogType.Assert, "Sensor sizes must match.");
-            LogAssert.Expect(LogType.Assert, "Sensor sizes much match.");
+            LogAssert.Expect(LogType.Assert, "Sensor sizes must match.");
             validator.ValidateSensors(sensorList1);
         }
 
             var sensorList2 = new List<ISensor>() { new DummySensor(1), new DummySensor(9) };
             LogAssert.Expect(LogType.Assert, "Number of Sensors must match. 3 != 2");
             LogAssert.Expect(LogType.Assert, "Sensor dimensions must match.");
-            LogAssert.Expect(LogType.Assert, "Sensor sizes much match.");
+            LogAssert.Expect(LogType.Assert, "Sensor sizes must match.");
             validator.ValidateSensors(sensorList2);
 
             // Add the sensors in the other order
             LogAssert.Expect(LogType.Assert, "Sensor dimensions must match.");
-            LogAssert.Expect(LogType.Assert, "Sensor sizes much match.");
+            LogAssert.Expect(LogType.Assert, "Sensor sizes must match.");
             validator.ValidateSensors(sensorList1);
         }
     }

com.unity.ml-agents/Tests/Editor/MLAgentsEditModeTest.cs

     {
         public Action OnRequestDecision;
         ObservationWriter m_ObsWriter = new ObservationWriter();
-        public void RequestDecision(AgentInfo info, List<ISensor> sensors) {
-            foreach(var sensor in sensors){
+        public void RequestDecision(AgentInfo info, List<ISensor> sensors)
+        {
+            foreach (var sensor in sensors)
+            {
                 sensor.GetObservationProto(m_ObsWriter);
             }
             OnRequestDecision?.Invoke();
             agent1.SetPolicy(policy);
 
             StackingSensor sensor = null;
-            foreach(ISensor s in agent1.sensors){
-                if (s is  StackingSensor){
+            foreach (ISensor s in agent1.sensors)
+            {
+                if (s is  StackingSensor)
+                {
                     sensor = s as StackingSensor;
                 }
             }
             {
                 agent1.RequestDecision();
                 aca.EnvironmentStep();
-
             }
 
             policy.OnRequestDecision = () =>  SensorTestHelper.CompareObservation(sensor, new[] {18f, 19f, 21f});

com.unity.ml-agents/CHANGELOG.md

 and this project adheres to
 [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [1.0.2-preview] - 2020-05-19
+### Bug Fixes
+#### com.unity.ml-agents (C#)
+- Fix missing .meta file
+
+## [1.0.1-preview] - 2020-05-19
+### Bug Fixes
+#### com.unity.ml-agents (C#)
+- A bug that would cause the editor to go into a loop when a prefab was selected was fixed. (#3949)
+- BrainParameters.ToProto() no longer throws an exception if none of the fields have been set. (#3930)
+- The Barracuda dependency was upgraded to 0.7.1-preview. (#3977)
+#### ml-agents / ml-agents-envs / gym-unity (Python)
+- An issue was fixed where using `--initialize-from` would resume from the past step count. (#3962)
+- The gym wrapper error for the wrong number of agents now fires more consistently, and more details
+  were added to the error message when the input dimension is wrong. (#3963)
+
 ## [1.0.0-preview] - 2020-05-06
 
 ### Major Changes

com.unity.ml-agents/Runtime/Communicator/GrpcExtensions.cs

         {
             var agentInfoProto = ai.ToAgentInfoProto();
 
-            var agentActionProto = new AgentActionProto
+            var agentActionProto = new AgentActionProto();
+            if(ai.storedVectorActions != null)
-                VectorActions = { ai.storedVectorActions }
-            };
+                agentActionProto.VectorActions.AddRange(ai.storedVectorActions);
+            }
 
             return new AgentInfoActionPairProto
             {
             var brainParametersProto = new BrainParametersProto
             {
                 VectorActionSize = { bp.VectorActionSize },
-                VectorActionSpaceType =
-                    (SpaceTypeProto)bp.VectorActionSpaceType,
+                VectorActionSpaceType = (SpaceTypeProto) bp.VectorActionSpaceType,
-            brainParametersProto.VectorActionDescriptions.AddRange(bp.VectorActionDescriptions);
+            if(bp.VectorActionDescriptions != null)
+            {
+                brainParametersProto.VectorActionDescriptions.AddRange(bp.VectorActionDescriptions);
+            }
             return brainParametersProto;
         }
 
         /// </summary>
         public static DemonstrationMetaProto ToProto(this DemonstrationMetaData dm)
         {
+            var demonstrationName = dm.demonstrationName ?? "";
             var demoProto = new DemonstrationMetaProto
             {
                 ApiVersion = DemonstrationMetaData.ApiVersion,
-                DemonstrationName = dm.demonstrationName
+                DemonstrationName = demonstrationName
             };
             return demoProto;
         }

com.unity.ml-agents/Runtime/Sensors/SensorShapeValidator.cs

                     Debug.Assert(cachedShape.Length == sensorShape.Length, "Sensor dimensions must match.");
                     for (var j = 0; j < Mathf.Min(cachedShape.Length, sensorShape.Length); j++)
                     {
-                        Debug.Assert(cachedShape[j] == sensorShape[j], "Sensor sizes much match.");
+                        Debug.Assert(cachedShape[j] == sensorShape[j], "Sensor sizes must match.");
                     }
                 }
             }

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

     /// [OnDisable()]: https://docs.unity3d.com/ScriptReference/MonoBehaviour.OnDisable.html]
     /// [OnBeforeSerialize()]: https://docs.unity3d.com/ScriptReference/MonoBehaviour.OnBeforeSerialize.html
     /// [OnAfterSerialize()]: https://docs.unity3d.com/ScriptReference/MonoBehaviour.OnAfterSerialize.html
-    /// [Agents]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design-Agents.md
-    /// [Reinforcement Learning in Unity]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design.md
+    /// [Agents]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design-Agents.md
+    /// [Reinforcement Learning in Unity]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design.md
-    /// [Unity ML-Agents Toolkit manual]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Readme.md
+    /// [Unity ML-Agents Toolkit manual]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Readme.md
-    [HelpURL("https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/" +
+    [HelpURL("https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/" +
         "docs/Learning-Environment-Design-Agents.md")]
     [Serializable]
     [RequireComponent(typeof(BehaviorParameters))]
         /// for information about mixing reward signals from curiosity and Generative Adversarial
         /// Imitation Learning (GAIL) with rewards supplied through this method.
         ///
-        /// [Agents - Rewards]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design-Agents.md#rewards
-        /// [Reward Signals]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/ML-Agents-Overview.md#a-quick-note-on-reward-signals
+        /// [Agents - Rewards]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design-Agents.md#rewards
+        /// [Reward Signals]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/ML-Agents-Overview.md#a-quick-note-on-reward-signals
         /// </remarks>
         /// <param name="reward">The new value of the reward.</param>
         public void SetReward(float reward)
         /// for information about mixing reward signals from curiosity and Generative Adversarial
         /// Imitation Learning (GAIL) with rewards supplied through this method.
         ///
-        /// [Agents - Rewards]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design-Agents.md#rewards
-        /// [Reward Signals]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/ML-Agents-Overview.md#a-quick-note-on-reward-signals
+        /// [Agents - Rewards]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design-Agents.md#rewards
+        /// [Reward Signals]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/ML-Agents-Overview.md#a-quick-note-on-reward-signals
         ///</remarks>
         /// <param name="increment">Incremental reward value.</param>
         public void AddReward(float increment)
         /// implementing a simple heuristic function can aid in debugging agent actions and interactions
         /// with its environment.
         ///
-        /// [Demonstration Recorder]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design-Agents.md#recording-demonstrations
-        /// [Actions]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design-Agents.md#actions
+        /// [Demonstration Recorder]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design-Agents.md#recording-demonstrations
+        /// [Actions]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design-Agents.md#actions
         /// [GameObject]: https://docs.unity3d.com/Manual/GameObjects.html
         /// </remarks>
         /// <example>
         /// For more information about observations, see [Observations and Sensors].
         ///
         /// [GameObject]: https://docs.unity3d.com/Manual/GameObjects.html
-        /// [Observations and Sensors]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design-Agents.md#observations-and-sensors
+        /// [Observations and Sensors]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design-Agents.md#observations-and-sensors
         /// </remarks>
         public virtual void CollectObservations(VectorSensor sensor)
         {
         ///
         /// See [Agents - Actions] for more information on masking actions.
         ///
-        /// [Agents - Actions]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design-Agents.md#actions
+        /// [Agents - Actions]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design-Agents.md#actions
         /// </remarks>
         /// <seealso cref="OnActionReceived(float[])"/>
         public virtual void CollectDiscreteActionMasks(DiscreteActionMasker actionMasker)
         ///
         /// For more information about implementing agent actions see [Agents - Actions].
         ///
-        /// [Agents - Actions]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design-Agents.md#actions
+        /// [Agents - Actions]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design-Agents.md#actions
         /// </remarks>
         /// <param name="vectorAction">
         /// An array containing the action vector. The length of the array is specified

com.unity.ml-agents/Runtime/Demonstrations/DemonstrationRecorder.cs

     /// See [Imitation Learning - Recording Demonstrations] for more information.
     ///
     /// [GameObject]: https://docs.unity3d.com/Manual/GameObjects.html
-    /// [Imitation Learning - Recording Demonstrations]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs//Learning-Environment-Design-Agents.md#recording-demonstrations
+    /// [Imitation Learning - Recording Demonstrations]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs//Learning-Environment-Design-Agents.md#recording-demonstrations
     /// </remarks>
     [RequireComponent(typeof(Agent))]
     [AddComponentMenu("ML Agents/Demonstration Recorder", (int)MenuGroup.Default)]

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

         ///
         /// See [Agents - Actions] for more information on masking actions.
         ///
-        /// [Agents - Actions]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Learning-Environment-Design-Agents.md#actions
+        /// [Agents - Actions]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Learning-Environment-Design-Agents.md#actions
         /// </remarks>
         /// <param name="branch">The branch for which the actions will be masked.</param>
         /// <param name="actionIndices">The indices of the masked actions.</param>

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

  * API. For more information on each of these entities, in addition to how to
  * set-up a learning environment and train the behavior of characters in a
  * Unity scene, please browse our documentation pages on GitHub:
- * https://github.com/Unity-Technologies/ml-agents/tree/release_1_docs/docs/
+ * https://github.com/Unity-Technologies/ml-agents/tree/release_2_docs/docs/
  */
 
 namespace Unity.MLAgents
     /// fall back to inference or heuristic decisions. (You can also set agents to always use
     /// inference or heuristics.)
     /// </remarks>
-    [HelpURL("https://github.com/Unity-Technologies/ml-agents/tree/release_1_docs/" +
+    [HelpURL("https://github.com/Unity-Technologies/ml-agents/tree/release_2_docs/" +
         "docs/Learning-Environment-Design.md")]
     public class Academy : IDisposable
     {
         /// Unity package version of com.unity.ml-agents.
         /// This must match the version string in package.json and is checked in a unit test.
         /// </summary>
-        internal const string k_PackageVersion = "1.0.0-preview";
+        internal const string k_PackageVersion = "1.0.2-preview";
 
         const int k_EditorTrainingPort = 5004;
 

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

 [unity ML-Agents Toolkit]: https://github.com/Unity-Technologies/ml-agents
 [unity inference engine]: https://docs.unity3d.com/Packages/com.unity.barracuda@latest/index.html
 [package manager documentation]: https://docs.unity3d.com/Manual/upm-ui-install.html
-[installation instructions]: https://github.com/Unity-Technologies/ml-agents/blob/release_1_docs/docs/Installation.md
+[installation instructions]: https://github.com/Unity-Technologies/ml-agents/blob/release_2_docs/docs/Installation.md
 [github repository]: https://github.com/Unity-Technologies/ml-agents
 [python package]: https://github.com/Unity-Technologies/ml-agents
 [execution order of event functions]: https://docs.unity3d.com/Manual/ExecutionOrder.html

docs/Using-Tensorboard.md

 the --port option.
 
 **Note:** If you don't assign a `run-id` identifier, `mlagents-learn` uses the
-default string, "ppo". All the statistics will be saved to the same sub-folder
-and displayed as one session in TensorBoard. After a few runs, the displays can
-become difficult to interpret in this situation. You can delete the folders
-under the `summaries` directory to clear out old statistics.
+default string, "ppo". You can delete the folders under the `results` directory
+to clear out old statistics.
 
 On the left side of the TensorBoard window, you can select which of the training
 runs you want to display. You can select multiple run-ids to compare statistics.
 
 ```csharp
 var statsRecorder = Academy.Instance.StatsRecorder;
-statsSideChannel.Add("MyMetric", 1.0);
+statsRecorder.Add("MyMetric", 1.0);
 ```

docs/Learning-Environment-Create-New.md

   learning_rate: 3.0e-4
   learning_rate_schedule: linear
   max_steps: 5.0e4
+  memory_size: 128
   normalize: false
   num_epoch: 3
   num_layers: 2

docs/Training-ML-Agents.md

   normalize: false
   num_layers: 2
   time_horizon: 64
+  summary_freq: 10000
+  init_path: null
 
   # PPO-specific configs
   beta: 5.0e-3
     batch_size: 512
     num_epoch: 3
     samples_per_update: 0
-    init_path:
 
   reward_signals:
     # environment reward
       strength: 0.02
       gamma: 0.99
       encoding_size: 256
-      learning_rate: 3e-4
+      learning_rate: 3.0e-4
 
     # GAIL
     gail:
       demo_path: Project/Assets/ML-Agents/Examples/Pyramids/Demos/ExpertPyramid.demo
-      learning_rate: 3e-4
+      learning_rate: 3.0e-4
       use_actions: false
       use_vail: false
 
     `interval_2_max`], ...]
   - **sub-arguments** - `intervals`
 
-The implementation of the samplers can be found at
-`ml-agents-envs/mlagents_envs/sampler_class.py`.
+The implementation of the samplers can be found in the
+[sampler_class.py file](../ml-agents/mlagents/trainers/sampler_class.py).
 
 #### Defining a New Sampler Type
 

docs/Installation-Anaconda-Windows.md

 the ml-agents Conda environment by typing `activate ml-agents`)_:
 
 ```sh
-git clone --branch release_1 https://github.com/Unity-Technologies/ml-agents.git
+git clone --branch release_2 https://github.com/Unity-Technologies/ml-agents.git
-The `--branch release_1` option will switch to the tag of the latest stable
+The `--branch release_2` option will switch to the tag of the latest stable
 release. Omitting that will get the `master` branch which is potentially
 unstable.
 

docs/Installation.md

 of our tutorials / guides assume you have access to our example environments).
 
 ```sh
-git clone --branch release_1 https://github.com/Unity-Technologies/ml-agents.git
+git clone --branch release_2 https://github.com/Unity-Technologies/ml-agents.git
-The `--branch release_1` option will switch to the tag of the latest stable
+The `--branch release_2` option will switch to the tag of the latest stable
 release. Omitting that will get the `master` branch which is potentially
 unstable.
 
 ML-Agents Toolkit for your purposes. If you plan to contribute those changes
-back, make sure to clone the `master` branch (by omitting `--branch release_1`
+back, make sure to clone the `master` branch (by omitting `--branch release_2`
 from the command above). See our
 [Contributions Guidelines](../com.unity.ml-agents/CONTRIBUTING.md) for more
 information on contributing to the ML-Agents Toolkit.

docs/Training-on-Amazon-Web-Service.md

 2. Clone the ML-Agents repo and install the required Python packages
 
    ```sh
-   git clone --branch release_1 https://github.com/Unity-Technologies/ml-agents.git
+   git clone --branch release_2 https://github.com/Unity-Technologies/ml-agents.git
    cd ml-agents/ml-agents/
    pip3 install -e .
    ```

com.unity.ml-agents/Tests/Editor/Communicator/GrpcExtensionsTests.cs

+using NUnit.Framework;
+using UnityEngine;
+using Unity.MLAgents.Policies;
+using Unity.MLAgents.Demonstrations;
+using Unity.MLAgents.Sensors;
+
+namespace Unity.MLAgents.Tests
+{
+    [TestFixture]
+    public class GrpcExtensionsTests
+    {
+        [Test]
+        public void TestDefaultBrainParametersToProto()
+        {
+            // Should be able to convert a default instance to proto.
+            var brain = new BrainParameters();
+            brain.ToProto("foo", false);
+        }
+
+        [Test]
+        public void TestDefaultAgentInfoToProto()
+        {
+            // Should be able to convert a default instance to proto.
+            var agentInfo = new AgentInfo();
+            agentInfo.ToInfoActionPairProto();
+            agentInfo.ToAgentInfoProto();
+        }
+
+        [Test]
+        public void TestDefaultDemonstrationMetaDataToProto()
+        {
+            // Should be able to convert a default instance to proto.
+            var demoMetaData = new DemonstrationMetaData();
+            demoMetaData.ToProto();
+        }
+    }
+}

com.unity.ml-agents/Tests/Editor/Communicator/GrpcExtensionsTests.cs.meta

+fileFormatVersion: 2
+guid: 7aa28d0e370064c18bb8a913417ad21d
+MonoImporter:
+  externalObjects: {}
+  serializedVersion: 2
+  defaultReferences: []
+  executionOrder: 0
+  icon: {instanceID: 0}
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: 

docs/Versioning.md

+# ML-Agents Versioning
+
+## Context
+As the ML-Agents project evolves into a more mature product, we want to communicate the process
+we use to version our packages and the data that flows into, through, and out of them clearly.
+Our project now has four packages (1 Unity, 3 Python) along with artifacts that are produced as
+well as consumed.  This document covers the versioning for these packages and artifacts.
+
+## GitHub Releases
+Up until now, all packages were in lockstep in-terms of versioning. As a result, the GitHub releases
+were tagged with the version of all those packages (e.g. v0.15.0, v0.15.1) and labeled accordingly.
+With the decoupling of package versions, we now need to revisit our GitHub release tagging.
+The proposal is that we move towards an integer release numbering for our repo and each such
+release will call out specific version upgrades of each package. For instance, with
+[the April 30th release](https://github.com/Unity-Technologies/ml-agents/releases/tag/release_1),
+we will have:
+- GitHub Release 1 (branch name: *release_1_branch*)
+  - com.unity.ml-agents release 1.0.0
+  - ml-agents release 0.16.0
+  - ml-agents-envs release 0.16.0
+  - gym-unity release 0.16.0
+
+Our release cadence will not be affected by these versioning changes.  We will keep having
+monthly releases to fix bugs and release new features.
+
+## Packages
+All of the software packages, and their generated artifacts will be versioned.  Any automation
+tools will not be versioned.
+
+### Unity package
+Package name: com.unity.ml-agents
+- Versioned following [Semantic Versioning Guidelines](https://www.semver.org)
+- This package consumes an artifact of the training process: the `.nn` file.  These files
+    are integer versioned and currently at version 2. The com.unity.ml-agents package
+    will need to support the version of `.nn` files which existed at its 1.0.0 release.
+    For example, consider that com.unity.ml-agents is at version 1.0.0 and the NN files
+    are at version 2.  If the NN files change to version 3, the next release of
+    com.unity.ml-agents at version 1.1.0 guarantees it will be able to read both of these
+    formats.  If the NN files were to change to version 4 and com.unity.ml-agents to
+    version 2.0.0, support for NN versions 2 and 3 could be dropped for com.unity.ml-agents
+    version 2.0.0.
+- This package produces one artifact, the `.demo` files.  These files will have integer
+    versioning. This means their version will increment by 1 at each change.  The
+    com.unity.ml-agents package must be backward compatible with version changes
+    that occur between minor versions.
+- To summarize, the artifacts produced and consumed by com.unity.ml-agents are guaranteed
+    to be supported for 1.x.x versions of com.unity.ml-agents.  We intend to provide stability
+    for our users by moving to a 1.0.0 release of com.unity.ml-agents.
+
+
+### Python Packages
+Package names: ml-agents / ml-agents-envs / gym-unity
+- The python packages remain in "Beta."  This means that breaking changes to the public
+    API of the python packages can change without having to have a major version bump.
+    Historically, the python and C# packages were in version lockstep.  This is no longer
+    the case.  The python packages will remain in lockstep with each other for now, while the
+    C# package will follow its own versioning as is appropriate.  However, the python package
+    versions may diverge in the future.
+- While the python packages will remain in Beta for now, we acknowledge that the most
+    heavily used portion of our python interface is the `mlagents-learn` CLI and strive
+    to make this part of our API backward compatible. We are actively working on this and
+    expect to have a stable CLI in the next few weeks.
+
+## Communicator
+
+Packages which communicate: com.unity.ml-agents / ml-agents-envs
+
+Another entity of the ML-Agents Toolkit that requires versioning is the communication layer
+between C# and Python, which will follow also semantic versioning.  This guarantees a level of
+backward compatibility between different versions of C# and Python packages which communicate.
+Any Communicator version 1.x.x of the Unity package should be compatible with any 1.x.x
+Communicator Version in Python.
+
+An RLCapabilities struct keeps track of which features exist. This struct is passed from C# to
+Python, and another from Python to C#.  With this feature level granularity, we can notify users
+more specifically about feature limitations based on what's available in both C# and Python.
+These notifications will be logged to the python terminal, or to the Unity Editor Console.
+
+
+## Side Channels
+
+The communicator is what manages data transfer between Unity and Python for the core
+training loop. Side Channels are another means of data transfer between Unity and Python.
+Side Channels are not versioned, but have been designed to support backward compatibility
+for what they are. As of today, we provide 4 side channels:
+- FloatProperties: shared float data between Unity - Python (bidirectional)
+- RawBytes: raw data that can be sent Unity - Python (bidirectional)
+- EngineConfig: a set of numeric fields in a pre-defined order sent from Python to Unity
+- Stats: (name, value, agg) messages sent from Unity to Python
+
+Aside from the specific implementations of side channels we provide (and use ourselves),
+the Side Channel interface is made available for users to create their own custom side
+channels. As such, we guarantee that the built in SideChannel interface between Unity and
+Python is backward compatible in packages that share the same major version.
+