Updating the NN models (#3632)

* Updating the NN models

* Update gridworld

* [skip ci] Update BallHard

* Update hallway

.circleci/config.yml

       pip_constraints:
         type: string
         description: Constraints file that is passed to "pip install". We constraint older versions of libraries for older python runtime, in order to help ensure compatibility.
+      enforce_onnx_conversion:
+        type: integer
+        default: 0
+        description: Whether to raise an exception if ONNX models couldn't be saved.
     executor: << parameters.executor >>
     working_directory: ~/repo
 
+      TEST_ENFORCE_ONNX_CONVERSION: << parameters.enforce_onnx_conversion >>
 
     steps:
       - checkout
           pyversion: 3.7.3
           # Test python 3.7 with the newest supported versions
           pip_constraints: test_constraints_max_tf1_version.txt
+          # Make sure ONNX conversion passes here (recent version of tensorflow 1.x)
+          enforce_onnx_conversion: 1
       - build_python:
           name: python_3.7.3+tf2
           executor: python373

README.md

 * Unity environment control from Python
 * 15+ sample Unity environments
 * Two deep reinforcement learning algorithms,
-[Proximal Policy Optimization](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Training-PPO.md)
- (PPO) and [Soft Actor-Critic](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Training-SAC.md)
+[Proximal Policy Optimization](docs/Training-PPO.md)
+ (PPO) and [Soft Actor-Critic](docs/Training-SAC.md)
-* Built-in support for [Imitation Learning](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Training-Imitation-Learning.md) through Behavioral Cloning or Generative Adversarial Imitation Learning
+* 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
 ## Releases & Documentation
-**Our latest, stable release is 0.14.1. Click
-[here](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Readme.md) to
+**Our latest, stable release is 0.15.0. 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
 
 | **Version** | **Release Date** | **Source** | **Documentation** | **Download** |
 |:-------:|:------:|:-------------:|:-------:|:------------:|
-| **master** (unstable) | -- | [source](https://github.com/Unity-Technologies/ml-agents/tree/master) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/master/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/master.zip) |
-| **0.14.1** (latest stable release) | February 26, 2020 | **[source](https://github.com/Unity-Technologies/ml-agents/tree/latest_release)** |  **[docs](https://github.com/Unity-Technologies/ml-agents/tree/latest_release/docs/Readme.md)** | **[download](https://github.com/Unity-Technologies/ml-agents/archive/latest_release.zip)** |
+| **0.14.1** | 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) |
 | **0.13.1**  | January 21, 2020 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.13.1) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.13.1/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.13.1.zip) |
 | **0.13.0**  | January 8, 2020 | [source](https://github.com/Unity-Technologies/ml-agents/tree/0.13.0) |  [docs](https://github.com/Unity-Technologies/ml-agents/tree/0.13.0/docs/Readme.md) | [download](https://github.com/Unity-Technologies/ml-agents/archive/0.13.0.zip) |

test_constraints_min_version.txt

 numpy==1.14.1
 Pillow==4.2.1
 protobuf==3.6
-tensorflow==1.7
+tensorflow==1.7.0
 h5py==2.9.0

test_requirements.txt

 pytest-cov==2.6.1
 pytest-xdist
 
-# Tests install onnx and tf2onnx, but this doesn't support tensorflow>=2.0.0
-# Since we test tensorflow2.0 with python3.7, exclude it based on the python version
-tf2onnx>=1.5.5; python_version < '3.7'
+tf2onnx>=1.5.5

test_constraints_max_tf1_version.txt

 # For projects with upper bounds, we should periodically update this list to the latest release version
 grpcio>=1.23.0
 numpy>=1.17.2
-# Temporary workaround for https://github.com/tensorflow/tensorflow/issues/36179 and https://github.com/tensorflow/tensorflow/issues/36188
-tensorflow>=1.14.0,<1.15.1
+tensorflow>=1.15.2,<2.0.0
 h5py>=2.10.0

config/gail_config.yaml

     hidden_units: 128
     lambd: 0.95
     learning_rate: 3.0e-4
-    max_steps: 5.0e4
+    max_steps: 5.0e5
     memory_size: 256
     normalize: false
     num_epoch: 3

config/trainer_config.yaml

     buffer_size: 12000
     summary_freq: 12000
     time_horizon: 1000
-    max_steps: 5.0e5
+    max_steps: 5.0e6
     beta: 0.001
     reward_signals:
         extrinsic:

docs/Unity-Inference-Engine.md

  * ONNX (`.onnx`) files use an [industry-standard open format](https://onnx.ai/about.html) produced by the [tf2onnx package](https://github.com/onnx/tensorflow-onnx).
 
 Export to ONNX is currently considered beta. To enable it, make sure `tf2onnx>=1.5.5` is installed in pip.
-tf2onnx does not currently support tensorflow 2.0.0 or later.
+tf2onnx does not currently support tensorflow 2.0.0 or later, or earlier than 1.12.0.
 
 ## Using the Unity Inference Engine
 

docs/Migrating.md

 
 # Migrating
 
-## Migrating from 0.14 to latest
+## Migrating from 0.14 to 0.15
 
 ### Important changes
 * The `Agent.CollectObservations()` virtual method now takes as input a `VectorSensor` sensor as argument. The `Agent.AddVectorObs()` methods were removed.

gym-unity/gym_unity/__init__.py

-__version__ = "0.15.0.dev0"
+__version__ = "0.15.0"

ml-agents-envs/mlagents_envs/__init__.py

-__version__ = "0.15.0.dev0"
+__version__ = "0.15.0"

ml-agents/mlagents/model_serialization.py

+from distutils.util import strtobool
+import os
+from distutils.version import LooseVersion
 
 try:
     import onnx
 from tensorflow.python.platform import gfile
 from tensorflow.python.framework import graph_util
 from mlagents.trainers import tensorflow_to_barracuda as tf2bc
+
+if LooseVersion(tf.__version__) < LooseVersion("1.12.0"):
+    # ONNX is only tested on 1.12.0 and later
+    ONNX_EXPORT_ENABLED = False
+
 
 logger = logging.getLogger("mlagents.trainers")
 
         logger.info(f"Exported {settings.model_path}.nn file")
 
     # Save to onnx too (if we were able to import it)
-    if ONNX_EXPORT_ENABLED and settings.convert_to_onnx:
-        try:
-            onnx_graph = convert_frozen_to_onnx(settings, frozen_graph_def)
-            onnx_output_path = settings.model_path + ".onnx"
-            with open(onnx_output_path, "wb") as f:
-                f.write(onnx_graph.SerializeToString())
-            logger.info(f"Converting to {onnx_output_path}")
-        except Exception:
-            logger.exception(
-                "Exception trying to save ONNX graph. Please report this error on "
-                "https://github.com/Unity-Technologies/ml-agents/issues and "
-                "attach a copy of frozen_graph_def.pb"
+    if ONNX_EXPORT_ENABLED:
+        if settings.convert_to_onnx:
+            try:
+                onnx_graph = convert_frozen_to_onnx(settings, frozen_graph_def)
+                onnx_output_path = settings.model_path + ".onnx"
+                with open(onnx_output_path, "wb") as f:
+                    f.write(onnx_graph.SerializeToString())
+                logger.info(f"Converting to {onnx_output_path}")
+            except Exception:
+                # Make conversion errors fatal depending on environment variables (only done during CI)
+                if _enforce_onnx_conversion():
+                    raise
+                logger.exception(
+                    "Exception trying to save ONNX graph. Please report this error on "
+                    "https://github.com/Unity-Technologies/ml-agents/issues and "
+                    "attach a copy of frozen_graph_def.pb"
+                )
+
+    else:
+        if _enforce_onnx_conversion():
+            # Either we're on an old version of tensorflow, or the import failed.
+            raise RuntimeError(
+                "ONNX conversion enforced, but ONNX_EXPORT_ENABLED was false."
             )
 
 
     for n in nodes:
         logger.info("\t" + n)
     return nodes
+
+
+def _enforce_onnx_conversion() -> bool:
+    env_var_name = "TEST_ENFORCE_ONNX_CONVERSION"
+    if env_var_name not in os.environ:
+        return False
+
+    val = os.environ[env_var_name]
+    try:
+        # This handles e.g. "false" converting reasonably to False
+        return strtobool(val)
+    except Exception:
+        return False

ml-agents/mlagents/trainers/__init__.py

-__version__ = "0.15.0.dev0"
+__version__ = "0.15.0"

ml-agents/mlagents/trainers/learn.py

 from mlagents_envs.side_channel.side_channel import SideChannel
 from mlagents_envs.side_channel.engine_configuration_channel import EngineConfig
 from mlagents_envs.exception import UnityEnvironmentException
-from mlagents_envs.timers import hierarchical_timer
+from mlagents_envs.timers import hierarchical_timer, get_timer_tree
 from mlagents.logging_util import create_logger
 
 
         tc.start_learning(env_manager)
     finally:
         env_manager.close()
+        write_timing_tree(summaries_dir, options.run_id)
+
+
+def write_timing_tree(summaries_dir: str, run_id: str) -> None:
+    timing_path = f"{summaries_dir}/{run_id}_timers.json"
+    try:
+        with open(timing_path, "w") as f:
+            json.dump(get_timer_tree(), f, indent=4)
+    except FileNotFoundError:
+        logging.warning(
+            f"Unable to save to {timing_path}. Make sure the directory exists"
+        )
 
 
 def create_sampler_manager(sampler_config, run_seed=None):

ml-agents/mlagents/trainers/trainer_controller.py

 
 import os
 import sys
-import json
 import logging
 from typing import Dict, Optional, Set
 from collections import defaultdict
     UnityCommunicationException,
 )
 from mlagents.trainers.sampler_class import SamplerManager
-from mlagents_envs.timers import hierarchical_timer, get_timer_tree, timed
+from mlagents_envs.timers import hierarchical_timer, timed
 from mlagents.trainers.trainer import Trainer
 from mlagents.trainers.meta_curriculum import MetaCurriculum
 from mlagents.trainers.trainer_util import TrainerFactory
             "Learning was interrupted. Please wait while the graph is generated."
         )
         self._save_model()
-
-    def _write_timing_tree(self) -> None:
-        timing_path = f"{self.summaries_dir}/{self.run_id}_timers.json"
-        try:
-            with open(timing_path, "w") as f:
-                json.dump(get_timer_tree(), f, indent=4)
-        except FileNotFoundError:
-            self.logger.warning(
-                f"Unable to save to {timing_path}. Make sure the directory exists"
-            )
 
     def _export_graph(self):
         """
             pass
         if self.train_model:
             self._export_graph()
-        self._write_timing_tree()
 
     def end_trainer_episodes(
         self, env: EnvManager, lessons_incremented: Dict[str, bool]

com.unity.ml-agents/Tests/Editor/PublicAPI/PublicApiValidation.cs

             var agent = gameObject.AddComponent<PublicApiAgent>();
             // Make sure we can set the behavior type correctly after the agent is added
             behaviorParams.behaviorType = BehaviorType.InferenceOnly;
+            // Can't actually create an Agent with InferenceOnly and no model, so change back
+            behaviorParams.behaviorType = BehaviorType.Default;
 
             // TODO -  not internal yet
             // var decisionRequester = gameObject.AddComponent<DecisionRequester>();

com.unity.ml-agents/package.json

 {
-	"name": "com.unity.ml-agents",
-	"displayName":"ML Agents",
-	"version": "0.14.1-preview",
-	"unity": "2018.4",
-	"description": "Add interactivity to your game with Machine Learning Agents trained using Deep Reinforcement Learning.",
-	"dependencies": {
-		"com.unity.barracuda": "0.6.1-preview"
-	}
-}
+  "name": "com.unity.ml-agents",
+  "displayName": "ML Agents",
+  "version": "0.15.0-preview",
+  "unity": "2018.4",
+  "description": "Add interactivity to your game with Machine Learning Agents trained using Deep Reinforcement Learning.",
+  "dependencies": {
+    "com.unity.barracuda": "0.6.1-preview"
+  }
+}

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

             if (brainParameters != null)
             {
                 var failedChecks = Inference.BarracudaModelParamLoader.CheckModel(
-                    barracudaModel, brainParameters, sensorComponents);
+                    barracudaModel, brainParameters, sensorComponents, behaviorParameters.behaviorType
+                );
                 foreach (var check in failedChecks)
                 {
                     if (check != null)

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

         /// 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 = "0.14.1-preview";
+        internal const string k_PackageVersion = "0.15.0-preview";
 
         const int k_EditorTrainingPort = 5004;
 

com.unity.ml-agents/Runtime/Inference/BarracudaModelParamLoader.cs

         /// </param>
         /// <param name="sensorComponents">Attached sensor components</param>
         /// <returns>The list the error messages of the checks that failed</returns>
-        public static IEnumerable<string> CheckModel(Model model, BrainParameters brainParameters, SensorComponent[] sensorComponents)
+        public static IEnumerable<string> CheckModel(Model model, BrainParameters brainParameters,
+            SensorComponent[] sensorComponents, BehaviorType behaviorType = BehaviorType.Default)
-                failedModelChecks.Add(
-                    "There is no model for this Brain, cannot run inference. " +
-                    "(But can still train)");
+                var errorMsg = "There is no model for this Brain; cannot run inference. ";
+                if (behaviorType == BehaviorType.InferenceOnly)
+                {
+                    errorMsg += "Either assign a model, or change to a different Behavior Type.";
+                }
+                else
+                {
+                    errorMsg += "(But can still train)";
+                }
+                failedModelChecks.Add(errorMsg);
                 return failedModelChecks;
             }
 

com.unity.ml-agents/Runtime/Policies/BehaviorParameters.cs

                 case BehaviorType.HeuristicOnly:
                     return new HeuristicPolicy(heuristic);
                 case BehaviorType.InferenceOnly:
+                {
+                    if (m_Model == null)
+                    {
+                        var behaviorType = BehaviorType.InferenceOnly.ToString();
+                        throw new UnityAgentsException(
+                            $"Can't use Behavior Type {behaviorType} without a model. " +
+                            "Either assign a model, or change to a different Behavior Type."
+                        );
+                    }
+                }
                 case BehaviorType.Default:
                     if (Academy.Instance.IsCommunicatorOn)
                     {

com.unity.ml-agents/CHANGELOG.md

 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
 
-## [Unreleased]
+## [0.15.0-preview] - 2020-03-18
 ### Major Changes
  - `Agent.CollectObservations` now takes a VectorSensor argument. (#3352, #3389)
  - Added `Agent.CollectDiscreteActionMasks` virtual method with a `DiscreteActionMasker` argument to specify which discrete actions are unavailable to the Agent. (#3525)
  - Fixed an issue when using GAIL with less than `batch_size` number of demonstrations. (#3591)
  - The interfaces to the `SideChannel` classes (on C# and python) have changed to use new  `IncomingMessage` and `OutgoingMessage` classes. These should make reading and writing data to the channel easier. (#3596)
  - Updated the ExpertPyramid.demo example demonstration file (#3613)
+ - Updated project version for example environments to 2018.4.18f1. (#3618)
+ - Changed the Product Name in the example environments to remove spaces, so that the default build executable file doesn't contain spaces. (#3612)
 
 ## [0.14.1-preview] - 2020-02-25
 

Project/Packages/manifest.json

 {
   "dependencies": {
     "com.unity.ads": "2.0.8",
-    "com.unity.analytics": "3.2.2",
+    "com.unity.analytics": "3.2.3",
     "com.unity.collab-proxy": "1.2.15",
     "com.unity.ml-agents": "file:../../com.unity.ml-agents",
     "com.unity.package-manager-ui": "2.0.8",
     "com.unity.modules.wind": "1.0.0",
     "com.unity.modules.xr": "1.0.0"
   },
-  "testables" : [
+  "testables": [
     "com.unity.ml-agents"
   ]
 }

Project/ProjectSettings/ProjectVersion.txt

-m_EditorVersion: 2018.4.14f1
+m_EditorVersion: 2018.4.18f1

Project/ProjectSettings/ProjectSettings.asset

   useOnDemandResources: 0
   accelerometerFrequency: 60
   companyName: Unity Technologies
-  productName: Unity Environment
+  productName: UnityEnvironment
-  m_ShowUnitySplashScreen: 0
+  m_ShowUnitySplashScreen: 1
   m_ShowUnitySplashLogo: 1
   m_SplashScreenOverlayOpacity: 1
   m_SplashScreenAnimation: 1
   xboxOneMonoLoggingLevel: 0
   xboxOneLoggingLevel: 1
   xboxOneDisableEsram: 0
+  xboxOneEnableTypeOptimization: 0
   xboxOnePresentImmediateThreshold: 0
   switchQueueCommandMemory: 1048576
   switchQueueControlMemory: 16384

Project/Assets/ML-Agents/Examples/Template/Scene.unity

 --- !u!104 &2
 RenderSettings:
   m_ObjectHideFlags: 0
-  serializedVersion: 8
+  serializedVersion: 9
   m_Fog: 0
   m_FogColor: {r: 0.5, g: 0.5, b: 0.5, a: 1}
   m_FogMode: 3
   m_CustomReflection: {fileID: 0}
   m_Sun: {fileID: 0}
   m_IndirectSpecularColor: {r: 0, g: 0, b: 0, a: 1}
+  m_UseRadianceAmbientProbe: 0
 --- !u!157 &3
 LightmapSettings:
   m_ObjectHideFlags: 0
     m_BounceScale: 1
     m_IndirectOutputScale: 1
     m_AlbedoBoost: 1
-    m_TemporalCoherenceThreshold: 1
-    serializedVersion: 9
+    serializedVersion: 10
-    m_TextureWidth: 1024
-    m_TextureHeight: 1024
+    m_AtlasSize: 1024
     m_AO: 0
     m_AOMaxDistance: 1
     m_CompAOExponent: 1
 --- !u!1 &762086410
 GameObject:
   m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  serializedVersion: 5
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  serializedVersion: 6
   m_Component:
   - component: {fileID: 762086412}
   - component: {fileID: 762086411}
 --- !u!108 &762086411
 Light:
   m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 762086410}
   m_Enabled: 1
   serializedVersion: 8
     serializedVersion: 2
     m_Bits: 4294967295
   m_Lightmapping: 4
+  m_LightShadowCasterMode: 0
   m_AreaSize: {x: 1, y: 1}
   m_BounceIntensity: 1
   m_ColorTemperature: 6570
 --- !u!4 &762086412
 Transform:
   m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 762086410}
   m_LocalRotation: {x: 0.40821788, y: -0.23456968, z: 0.10938163, w: 0.8754261}
   m_LocalPosition: {x: 0, y: 3, z: 0}
 --- !u!1 &1223085755
 GameObject:
   m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  serializedVersion: 5
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  serializedVersion: 6
   m_Component:
   - component: {fileID: 1223085757}
   - component: {fileID: 1223085756}
 --- !u!114 &1223085756
 MonoBehaviour:
   m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 1223085755}
   m_Enabled: 1
   m_EditorHideFlags: 0
-  brain: {fileID: 0}
-    agentCameras: []
-    resetOnDone: 1
-    onDemandDecision: 0
-    numberOfActionsBetweenDecisions: 1
+  hasUpgradedFromAgentParameters: 1
+  maxStep: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 1223085755}
   m_LocalRotation: {x: 0, y: 0, z: 0, w: 1}
   m_LocalPosition: {x: 0.71938086, y: 0.27357092, z: 4.1970553}
 --- !u!1 &1574236047
 GameObject:
   m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  serializedVersion: 5
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  serializedVersion: 6
-  - component: {fileID: 1574236048}
   m_Layer: 0
   m_Name: Academy
   m_TagString: Untagged
   m_IsActive: 1
---- !u!114 &1574236048
-MonoBehaviour:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 1574236047}
-  m_Enabled: 1
-  m_EditorHideFlags: 0
-  m_Script: {fileID: 11500000, guid: 9af83cd96d4bc4088a966af174446d1b, type: 3}
-  m_Name: 
-  m_EditorClassIdentifier: 
-  broadcastHub:
-    broadcastingBrains: []
-    _brainsToControl: []
-  maxSteps: 0
-  trainingConfiguration:
-    width: 80
-    height: 80
-    qualityLevel: 0
-    timeScale: 100
-    targetFrameRate: 60
-  inferenceConfiguration:
-    width: 1024
-    height: 720
-    qualityLevel: 1
-    timeScale: 1
-    targetFrameRate: 60
-  resetParameters:
-    resetParameters: []
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 1574236047}
   m_LocalRotation: {x: 0, y: 0, z: 0, w: 1}
   m_LocalPosition: {x: 0.71938086, y: 0.27357092, z: 4.1970553}
 --- !u!1 &1715640920
 GameObject:
   m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  serializedVersion: 5
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  serializedVersion: 6
-  - component: {fileID: 1715640923}
   - component: {fileID: 1715640922}
   - component: {fileID: 1715640921}
   m_Layer: 0
 --- !u!81 &1715640921
 AudioListener:
   m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
-  m_GameObject: {fileID: 1715640920}
-  m_Enabled: 1
---- !u!92 &1715640923
-Behaviour:
-  m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
+  m_projectionMatrixMode: 1
+  m_SensorSize: {x: 36, y: 24}
+  m_LensShift: {x: 0, y: 0}
+  m_GateFitMode: 2
+  m_FocalLength: 50
   m_NormalizedViewPortRect:
     serializedVersion: 2
     x: 0
 --- !u!4 &1715640925
 Transform:
   m_ObjectHideFlags: 0
-  m_PrefabParentObject: {fileID: 0}
-  m_PrefabInternal: {fileID: 0}
+  m_CorrespondingSourceObject: {fileID: 0}
+  m_PrefabInstance: {fileID: 0}
+  m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 1715640920}
   m_LocalRotation: {x: 0, y: 0, z: 0, w: 1}
   m_LocalPosition: {x: 0, y: 1, z: -10}

Project/Assets/ML-Agents/Examples/3DBall/Scenes/3DBall.unity

   m_ReflectionIntensity: 1
   m_CustomReflection: {fileID: 0}
   m_Sun: {fileID: 0}
-  m_IndirectSpecularColor: {r: 0.4497121, g: 0.49977785, b: 0.57563704, a: 1}
+  m_IndirectSpecularColor: {r: 0.44971162, g: 0.49977726, b: 0.5756362, a: 1}
   m_UseRadianceAmbientProbe: 0
 --- !u!157 &3
 LightmapSettings:
   m_Component:
   - component: {fileID: 807556627}
   - component: {fileID: 807556626}
-  - component: {fileID: 807556625}
   - component: {fileID: 807556624}
   - component: {fileID: 807556623}
   m_Layer: 0
   m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 807556622}
   m_Enabled: 1
---- !u!92 &807556625
-Behaviour:
-  m_ObjectHideFlags: 0
-  m_CorrespondingSourceObject: {fileID: 0}
-  m_PrefabInstance: {fileID: 0}
-  m_PrefabAsset: {fileID: 0}
-  m_GameObject: {fileID: 807556622}
-  m_Enabled: 1
 --- !u!20 &807556626
 Camera:
   m_ObjectHideFlags: 0
   m_Name: 
   m_EditorClassIdentifier: 
   gravityMultiplier: 1
-  monitorVerticalOffset: 0
   fixedDeltaTime: 0.02
   maximumDeltaTime: 0.33333334
   solverIterations: 6

Project/Assets/ML-Agents/Examples/3DBall/Scenes/3DBallHard.unity

   m_ReflectionIntensity: 1
   m_CustomReflection: {fileID: 0}
   m_Sun: {fileID: 0}
-  m_IndirectSpecularColor: {r: 0.4497121, g: 0.49977785, b: 0.57563704, a: 1}
+  m_IndirectSpecularColor: {r: 0.44971162, g: 0.49977726, b: 0.5756362, a: 1}
   m_UseRadianceAmbientProbe: 0
 --- !u!157 &3
 LightmapSettings:
   m_Component:
   - component: {fileID: 807556627}
   - component: {fileID: 807556626}
-  - component: {fileID: 807556625}
   - component: {fileID: 807556624}
   - component: {fileID: 807556623}
   m_Layer: 0
   m_GameObject: {fileID: 807556622}
   m_Enabled: 1
 --- !u!124 &807556624
-Behaviour:
-  m_ObjectHideFlags: 0
-  m_CorrespondingSourceObject: {fileID: 0}
-  m_PrefabInstance: {fileID: 0}
-  m_PrefabAsset: {fileID: 0}
-  m_GameObject: {fileID: 807556622}
-  m_Enabled: 1
---- !u!92 &807556625
 Behaviour:
   m_ObjectHideFlags: 0
   m_CorrespondingSourceObject: {fileID: 0}
   m_Name: 
   m_EditorClassIdentifier: 
   gravityMultiplier: 1
-  monitorVerticalOffset: 0
   fixedDeltaTime: 0.02
   maximumDeltaTime: 0.33333334
   solverIterations: 6

Project/Assets/ML-Agents/Examples/Basic/Scenes/Basic.unity

   m_Component:
   - component: {fileID: 1715640925}
   - component: {fileID: 1715640924}
-  - component: {fileID: 1715640923}
   - component: {fileID: 1715640922}
   - component: {fileID: 1715640921}
   m_Layer: 0
   m_GameObject: {fileID: 1715640920}
   m_Enabled: 1
 --- !u!124 &1715640922
-Behaviour:
-  m_ObjectHideFlags: 0
-  m_CorrespondingSourceObject: {fileID: 0}
-  m_PrefabInstance: {fileID: 0}
-  m_PrefabAsset: {fileID: 0}
-  m_GameObject: {fileID: 1715640920}
-  m_Enabled: 1
---- !u!92 &1715640923
 Behaviour:
   m_ObjectHideFlags: 0
   m_CorrespondingSourceObject: {fileID: 0}

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

-vector_observation����

action_masks����

action_probs/action_probsconcat_2/concatactionaction_output_shape������?action_output_shape




memory_size





version_number




is_continuous_control




add_3/y




Sum/reduction_indices




add_1/y




main_graph_0/hidden_0/BiasAdd
�����?
vector_observationmain_graph_0/hidden_0/kernel

�
main_graph_0/hidden_0/bias


�
main_graph_0/hidden_0/Mul2	�����?
main_graph_0/hidden_0/BiasAdddense/MatMul
�����?
main_graph_0/hidden_0/Muldense/kernel

�
<dense/MatMul/patch:0


�
action_probs/action_probs2�����?
dense/MatMul
strided_slice�



�����?
action_probs/action_probsstrided_slice_1�



�����?
action_masksSoftmax2�����?

strided_sliceadd_1d�����?Softmaxadd_1/yMulf�����?add_1strided_slice_1Sum������?MulSum/reduction_indicestruedivg�����?MulSumadd_3d�����?truedivadd_3/yLog_12r�����?
add_3concat_2/concat2�����?
Log_1action2�����?
concat_2/concat@@@���3�?���3Ȥ꾒+�=�5پܢ׻�B��(������:Ȫ�>ɒ�>��J�����!��C}��,��>0R�S���'fA���a��Q>d�<"S�>��>u�Ծui`>r�9�0��Cc��>���5�>��w��j�=#����Z>�Q����~>C)�=)ѽ6=�|��=.0u>K)s>J�>�^->/��>Ǹ5>�8Q�!Q%�/�Y>y:�;����n�Uߣ�i�m���X����<Yn���
��颾��s�*�Ѿ|2��L�>޷�=�O.�rN/>����nzz�SЋ>����)t��V�=�_>TY�>�C��]��˟<�ay=�ě>��
�-�Z��<�>� ��Ծ���=��˽���diǾzS߾�Ó�
2>��_>2�d>�>�	w���0��:���;�>�M˾#a�=a�>�%�����>+c�=w�f���7�
�U���=>��R=*�<˷��
a�=�پe\p�����]>O���A>�|3L=۽����J���m>,��*48>�D�>OKy�&��>����>�>��;����hp3���@��t�^>�==��'>���<�b���j
-���p��Y�>6�>|����>+�>Q���p1c>��Z�bI1=�I�>͋����������(_���=Z�j�G�U�^���Dp�<����o�>��H>�ъ=b=��=Q雾k�T>	��<���=�G�\P?��">x\#>�1S��Oӽ�����+)���=F��1]�?��=��	�G G>�D����>n�n>6����>������#>o�V=����b����>dI�=v�<�8�-)>����*�=�?)�ݼWT�>���>���>Ľo=gt�>��
N�>��1��C�~k\>���,��=Ig�>
[�>���=�Z�<��q=z�>�]�>�a}�o�8=8>?I-?P�>\�?u7�Bb>p�Y��{W�afK>�eӾ!?�+)?"?&�
?BB��0^.�� �<Yv�>�1羛H=`WR��b�>�'�>
vK>����/�`?����B ���?|վ�q%?�?=
? N?���&�.^�0|2?���=q���V>�?��!?��>Zk>h&ϾN�>j���
55�J�c>tc���>��?i{^>�`>���y�%
-�=�h�>�`��Mt�>[7?h?��?`��>���=#x.?u&8��(Ľy�>R����>�U�>*-�>]1�>&����-�9�?�>`�=���+?W�=�Ӽ���>�=�r��Ax�>g��Ĵ�����>�x�����>��>���>�T??�������[>�'�ƌѾ��?�56?���>}x-?��?Cn\���;��&�LT����>����	��>�R�>.�?J��>|�ʽ�;H��*=�	�Q{��ȵ�;�`�����>R��<���>m6�=�a$>�=>��n=�T���y>���>4�S���>)3��E\�>���3�=���<D鸾�.վ�X.�ʩҽ>�>��=�21�_�����%��l��g����N��Ȉ����=�<
�7��Ѣx>Ax'>�'v>�)�>}^�>�վ�>$o�<���=U���GY�=�&L�2p�=��s�:x+�Vm��۪���-<E�;'j�>���#�+?t_#?����?9�)?��"?��?��*?j���'?܂
-�_S	�Y9,?;�����(?ћ3?�� ?f�"?PH�y.�>;�@>�4쾕���T~оsg?
����m���"?
�>�޶>Q���
׾�q��U�?�վr*羺�?��澅�Ծ`?z�Ⱦ�۾t�?�Fݾ�z���?�E�>ٽ�>����=�wܾʃ?!d�>hx�>D���r�>Tb�>����i��w�ھ?C"�>�~�>I�������Z���%?{���J��U.?�8��O��}�#?��о@c¾Ց?#��>�j�>/��
+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�-?

Project/Assets/ML-Agents/Examples/Crawler/Scenes/CrawlerDynamicTarget.unity

   m_Component:
   - component: {fileID: 1392866532}
   - component: {fileID: 1392866531}
-  - component: {fileID: 1392866530}
   - component: {fileID: 1392866529}
   - component: {fileID: 1392866528}
   - component: {fileID: 1392866533}
   m_GameObject: {fileID: 1392866527}
   m_Enabled: 1
 --- !u!124 &1392866529
-Behaviour:
-  m_ObjectHideFlags: 0
-  m_CorrespondingSourceObject: {fileID: 0}
-  m_PrefabInstance: {fileID: 0}
-  m_PrefabAsset: {fileID: 0}
-  m_GameObject: {fileID: 1392866527}
-  m_Enabled: 1
---- !u!92 &1392866530
 Behaviour:
   m_ObjectHideFlags: 0
   m_CorrespondingSourceObject: {fileID: 0}
   m_Name: 
   m_EditorClassIdentifier: 
   gravityMultiplier: 1
-  monitorVerticalOffset: 1
   fixedDeltaTime: 0.01333
   maximumDeltaTime: 0.15
   solverIterations: 12

Project/Assets/ML-Agents/Examples/GridWorld/Scenes/GridWorld.unity

   m_ReflectionIntensity: 1
   m_CustomReflection: {fileID: 0}
   m_Sun: {fileID: 0}
-  m_IndirectSpecularColor: {r: 0.4497121, g: 0.49977785, b: 0.57563704, a: 1}
+  m_IndirectSpecularColor: {r: 0.44971162, g: 0.49977726, b: 0.5756362, a: 1}
   m_UseRadianceAmbientProbe: 0
 --- !u!157 &3
 LightmapSettings:
   m_Component:
   - component: {fileID: 99095116}
   - component: {fileID: 99095115}
-  - component: {fileID: 99095114}
   - component: {fileID: 99095113}
   m_Layer: 0
   m_Name: Main Camera
   m_PrefabAsset: {fileID: 0}
   m_GameObject: {fileID: 99095112}
   m_Enabled: 1
---- !u!92 &99095114
-Behaviour:
-  m_ObjectHideFlags: 0
-  m_CorrespondingSourceObject: {fileID: 0}
-  m_PrefabInstance: {fileID: 0}
-  m_PrefabAsset: {fileID: 0}
-  m_GameObject: {fileID: 99095112}
-  m_Enabled: 1
 --- !u!20 &99095115
 Camera:
   m_ObjectHideFlags: 0
   m_EditorClassIdentifier: 
   agentParameters:
     maxStep: 100
-    resetOnDone: 1
-    onDemandDecision: 1
-    numberOfActionsBetweenDecisions: 1
+  hasUpgradedFromAgentParameters: 1
+  maxStep: 100
   area: {fileID: 1795599557}
   timeBetweenDecisionsAtInference: 0.15
   renderCamera: {fileID: 797520692}
   m_InferenceDevice: 0
   m_BehaviorType: 0
   m_BehaviorName: GridWorld
-  m_TeamID: 0
-  m_useChildSensors: 1
+  TeamId: 0
+  m_UseChildSensors: 1
 --- !u!114 &125487791
 MonoBehaviour:
   m_ObjectHideFlags: 0
   m_Script: {fileID: 11500000, guid: 132e1194facb64429b007ea1edf562d0, type: 3}
   m_Name: 
   m_EditorClassIdentifier: 
-  renderTexture: {fileID: 8400000, guid: 114608d5384404f89bff4b6f88432958, type: 2}
-  sensorName: RenderTextureSensor
-  grayscale: 0
-  compression: 1
+  m_RenderTexture: {fileID: 8400000, guid: 114608d5384404f89bff4b6f88432958, type: 2}
+  m_SensorName: RenderTextureSensor
+  m_Grayscale: 0
+  m_Compression: 1
 --- !u!1 &260425459
 GameObject:
   m_ObjectHideFlags: 0

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

+using NUnit.Framework;
+using UnityEngine;
+using MLAgents;
+using MLAgents.Policies;
+
+namespace MLAgents.Tests
+{
+    [TestFixture]
+    public class BehaviorParameterTests
+    {
+        static float[] DummyHeuristic()
+        {
+            return null;
+        }
+
+        [Test]
+        public void TestNoModelInferenceOnlyThrows()
+        {
+            var gameObj = new GameObject();
+            var bp = gameObj.AddComponent<BehaviorParameters>();
+            bp.behaviorType = BehaviorType.InferenceOnly;
+
+            Assert.Throws<UnityAgentsException>(() =>
+            {
+                bp.GeneratePolicy(DummyHeuristic);
+            });
+        }
+    }
+}

com.unity.ml-agents/Tests/Editor/BehaviorParameterTests.cs.meta

+fileFormatVersion: 2
+guid: 877266b9e1bfe4330a68ab5f2da1836b
+MonoImporter:
+  externalObjects: {}
+  serializedVersion: 2
+  defaultReferences: []
+  executionOrder: 0
+  icon: {instanceID: 0}
+  userData: 
+  assetBundleName: 
+  assetBundleVariant: