Put back unreleased changes

* Updated the badge’s link to point to the newest doc version

* Replaced all of the doc to release_3_doc

* Update to release_3 in installation.md (#4144)

Co-authored-by: Yuan Gao <xiaomaogy88@gmail.com>
Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>

gym-unity/gym_unity/__init__.py

 # Version of the library that will be used to upload to pypi
-__version__ = "0.17.0"
+__version__ = "0.18.0.dev0"
-__release_tag__ = "release_3"
+__release_tag__ = None

DevProject/Packages/manifest.json

   "dependencies": {
     "com.unity.2d.sprite": "1.0.0",
     "com.unity.2d.tilemap": "1.0.0",
-    "com.unity.ads": "2.0.8",
+    "com.unity.ads": "3.4.4",
     "com.unity.analytics": "3.3.5",
     "com.unity.coding": "0.1.0-preview.13",
     "com.unity.collab-proxy": "1.2.16",
     "com.unity.multiplayer-hlapi": "1.0.4",
     "com.unity.package-manager-doctools": "1.1.1-preview.3",
-    "com.unity.package-validation-suite": "0.7.15-preview",
+    "com.unity.package-validation-suite": "0.11.0-preview",
-    "com.unity.test-framework": "1.1.11",
+    "com.unity.test-framework": "1.1.13",
-    "com.unity.xr.legacyinputhelpers": "1.3.8",
+    "com.unity.xr.legacyinputhelpers": "1.3.11",
     "com.unity.modules.ai": "1.0.0",
     "com.unity.modules.androidjni": "1.0.0",
     "com.unity.modules.animation": "1.0.0",

DevProject/ProjectSettings/ProjectVersion.txt

-m_EditorVersion: 2019.3.3f1
-m_EditorVersionWithRevision: 2019.3.3f1 (7ceaae5f7503)
+m_EditorVersion: 2019.3.11f1
+m_EditorVersionWithRevision: 2019.3.11f1 (ceef2d848e70)

ml-agents-envs/mlagents_envs/__init__.py

 # Version of the library that will be used to upload to pypi
-__version__ = "0.17.0"
+__version__ = "0.18.0.dev0"
-__release_tag__ = "release_3"
+__release_tag__ = None

docs/Learning-Environment-Design-Agents.md

 - `Agent.Heuristic()` - When the `Behavior Type` is set to `Heuristic Only` in
   the Behavior Parameters of the Agent, the Agent will use the `Heuristic()`
   method to generate the actions of the Agent. As such, the `Heuristic()` method
-  writes to a provided array of floats.
+  writes to the array of floats provided to the Heuristic method as argument.
+  __Note__: Do not create a new float array of action in the `Heuristic()` method,
+  as this will prevent writing floats to the original action array.
 
 As a concrete example, here is how the Ball3DAgent class implements these methods:
 

ml-agents/mlagents/trainers/__init__.py

 # Version of the library that will be used to upload to pypi
-__version__ = "0.17.0"
+__version__ = "0.18.0.dev0"
-__release_tag__ = "release_3"
+__release_tag__ = None

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

         /// <seealso cref="OnActionReceived(float[])"/> function, which receives this array and
         /// implements the corresponding agent behavior. See [Actions] for more information
         /// about agent actions.
+        /// Note : Do not create a new float array of action in the `Heuristic()` method,
+        /// as this will prevent writing floats to the original action array.
         ///
         /// An agent calls this `Heuristic()` function to make a decision when you set its behavior
         /// type to <see cref="BehaviorType.HeuristicOnly"/>. The agent also calls this function if

com.unity.ml-agents/CHANGELOG.md

 and this project adheres to
 [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Major Changes
+#### com.unity.ml-agents (C#)
+#### ml-agents / ml-agents-envs / gym-unity (Python)
+
+### Minor Changes
+#### com.unity.ml-agents (C#)
+#### ml-agents / ml-agents-envs / gym-unity (Python)
+
+### Bug Fixes
+#### com.unity.ml-agents (C#)
+#### ml-agents / ml-agents-envs / gym-unity (Python)
+
 ## [1.1.0-preview] - 2020-06-10
 ### Major Changes
 #### com.unity.ml-agents (C#)