Develop scriptable brains documentation #1249

vincentpierre · 2018-09-21T02:29:40Z

This PR is towards develop-scriptable-brains (and not develop). It contains the changes to the documentation that the feature "Brains as Scriptable Objects" require.

Internal Brains and External Brains are now Learning Brains
The process of creating brains now goes through Assets -> Create -> Ml-Agents
Brains are now scriptable objects
There is no longer BrainType different types of brains now correspond to different classes of instances of Brains
Still need to update pictures

awjuliani · 2018-09-24T22:11:48Z

docs/Basic-Guide.md

-Since we are going to build this environment to conduct training, we need to set
-the Brain used by the Agents to **External**. This allows the Agents to
+Since we are going to build this environment to conduct training, we need to add 
+the Brain to the training session. This allows the Agents to


Maybe specify that we mean the agents linked to that brain?

awjuliani · 2018-09-24T22:12:57Z

docs/Basic-Guide.md

-   object.
-2. Select its child object **Ball3DBrain**.
-3. In the Inspector window, set **Brain Type** to **External**.
+1. Give to the agents you want to train the **Ball3DBrain**. 


This is worded a little strangely. Perhaps "Assign the Ball3DBrain to the agents you would like to train.

awjuliani · 2018-09-24T22:13:47Z

docs/Getting-Started-with-Balance-Ball.md

-and **Internal** types work together — use **External** when training your
-Agents; use **Internal** when using the trained model. The **Heuristic** Brain
-allows you to hand-code the Agent's logic by extending the Decision class.
+There are 3 types of brains, you can create new ones by selecting `Assets -> 


This should be two sentences.

awjuliani · 2018-09-24T22:14:26Z

docs/Getting-Started-with-Balance-Ball.md

+Create -> ML-Agents -> Brain`.
+The **Learning Brain** is a brain that uses a Neural Network to take decisions.
+When the Brain is checked as `Train` in the Academy **Training Hub**, the 
+Neural Network will be trained by the external process. You can also use the


This is somewhat misleading, since there isn't a NN in Unity being trained, but the NN lives outside Unity.

awjuliani · 2018-09-24T22:15:07Z

docs/Learning-Environment-Create-New.md

 component later in the tutorial.

-### Add Empty GameObjects to Hold the Academy and Brain
+### Add Empty GameObjects to Hold the Academy


Add an Empty GameObject to hold the Academy ?

awjuliani · 2018-09-24T22:16:44Z

docs/Learning-Environment-Design-Learning-Brains.md

@@ -0,0 +1,75 @@
+# Learning Brains
+
+The **Learning Brain** work in different phases of


works differently in different phases?

awjuliani · 2018-09-24T22:17:29Z

docs/Learning-Environment-Design-Learning-Brains.md

+Academy's `Training Hub` and check the checkbox `Train`. When using a pretrained 
+model, just drag the Model file into the `Model` property of the **Learning Brain**.
+
+## Training Mode


I know we are calling this training, but maybe we should use somewhat more agnostic language here, in case people think it is only for training?

Since technically it is for external control.

awjuliani · 2018-09-24T22:19:33Z

docs/Migrating.md


+## Migrating from ML-Agents toolkit v0.5 to v0.6
+### Important
+* Brains are now Scriptable Objects instead of Monobehaviors. This will


Maybe give some recommendation about the best way to move a project that is using a lot of the old brains to use the new brains. Especially since the old functionality is removed.

@awjuliani I added a paragraph.

awjuliani · 2018-09-24T22:21:36Z

Comments mainly about wording of different things. Going through this raises in my mind the question of whether we want to rename the "Training Hub" to something more appropriate/descriptive.

…ns-documentation

xiaomaogy · 2018-09-26T22:58:03Z

docs/Learning-Environment-Design-Agents.md

 When using Discrete Actions, it is possible to specify that some actions are
 impossible for the next decision. Then the Agent is controlled by an External or
-Internal Brain, the Agent will be unable to perform the specified action. Note
+Learning Brain, the Agent will be unable to perform the specified action. Note


It should be External that gets corrected to Learning.

There is no external brain anymore

Yes I know, but you still say 'Then the Agent is controlled by an External or Learning Brain, the Agent will be unable to perform the specified action. Note', which mentions External.

xiaomaogy · 2018-09-26T23:07:42Z

Overall looks good to me.

* Initial Commit Ported most functionalities, still need to : - Documentation - Add Comments - Custom drawer for BrainParameters - Fix the UnitTests - Review Functionalities * Added Custom Drawer for the Brain Parameters * Improvements to the HubDrawer * Modified the Brain Editors * Minor bug fixes and UI changes * Modified the Help Boxes of the Drawers * Modified Brain class, renamed Initialize and made DecideAction virtual * Fix the UnityTests * Simpler Brain creation menu * Renamed Internal Brain to Learning Brain * modified the parameters to remove reference to External or Internal in the Protobuf objects * Updated the protobuf generated files * Fix the Pytests * Removed the graph scope from the Learning Brain * cleaner logic than try catch * Removed the isExternal field of the brain and put the isTraining logic into LearningBrain and Training Hub * Modified how the Brain finds the Academy * Removed refences to CoreBrain * Fix import bug * Addressed some comments * Remove useless imports * Added nice icons for the brains * Added a feature to deepcopy brain parameters between brains * Resolve drawer bug * Develop scriptable brains ball scene (#1233) * Created the Brains for the Ballance Ball Environment * Modified the Balance Ball Scene * Renamed Training Hub to Broadcast Hub * Added a comment * renamed SetToControlled to SetControlledExternally in the Learning Brain * Resolved errors in case ENABLE_TENSORFLOW is not activated * Update the BalanceBall Scene * Refactored the BrainParameters drawer * Addressed offline comments * Comments on the ResetParametersDrawer * refactired the BroadcastHubDrawer * Adding comments * Add comment on the horizontal bar * Added new comments * Refactor of the Editors * minor changes * Added documentation, Fixed a bug in the tenporary internal brain when TF# is disabled * Develop scriptable brains documentation (#1249) * Modified first docs * modified the markdown, not the images * Missing doc * Replaced Internal with Learned Brain * updated the images * Addressed some comments * Renamed Training Hub to Broadcast Hub * Forgot one file * Added new images * addressing comment * Fixed some typos * address comments on the code * addressed comments on documents * Resolving conflicts on the Learning Brain * Minor tweaks * Addressed Comments * Created a Clone method in the BrainParameters, created a new BrainParameters file, made a CumSum method * Added Unit Test

vincentpierre added 4 commits September 20, 2018 13:33

Modified first docs

f619cd5

modified the markdown, not the images

26acc95

Missing doc

0a7d150

Replaced Internal with Learned Brain

7556c03

vincentpierre requested a review from xiaomaogy September 21, 2018 02:29

vincentpierre mentioned this pull request Sep 21, 2018

Brains as Scriptable Objects #1250

Merged

12 tasks

vincentpierre added 2 commits September 20, 2018 19:59

Resolved the merge conflicts

8b473ff

updated the images

8dc7e45

awjuliani reviewed Sep 24, 2018

View reviewed changes

Addressed some comments

aff9682

vincentpierre requested a review from mmattar September 25, 2018 21:53

vincentpierre added 3 commits September 26, 2018 15:35

Renamed Training Hub to Broadcast Hub

d0253c1

Forgot one file

e18a091

Merge branch 'develop-scriptable-brains' into develop-scriptable-brai…

9cdf3e9

…ns-documentation

xiaomaogy reviewed Sep 26, 2018

View reviewed changes

vincentpierre added 3 commits September 26, 2018 16:31

Added new images

034caec

addressing comment

6854444

Fixed some typos

6cb87d9

vincentpierre merged commit 5b5375a into develop-scriptable-brains Oct 3, 2018

vincentpierre deleted the develop-scriptable-brains-documentation branch October 3, 2018 22:13

github-actions bot locked as resolved and limited conversation to collaborators May 19, 2021

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Develop scriptable brains documentation #1249

Develop scriptable brains documentation #1249

Uh oh!

vincentpierre commented Sep 21, 2018 •

edited

Loading

Uh oh!

awjuliani Sep 24, 2018

Uh oh!

awjuliani Sep 24, 2018

Uh oh!

awjuliani Sep 24, 2018

Uh oh!

awjuliani Sep 24, 2018

Uh oh!

awjuliani Sep 24, 2018

Uh oh!

awjuliani Sep 24, 2018

Uh oh!

awjuliani Sep 24, 2018

Uh oh!

awjuliani Sep 24, 2018

Uh oh!

awjuliani Sep 24, 2018

Uh oh!

vincentpierre Sep 25, 2018 •

edited

Loading

Uh oh!

awjuliani commented Sep 24, 2018

Uh oh!

xiaomaogy Sep 26, 2018

Uh oh!

vincentpierre Sep 26, 2018

Uh oh!

xiaomaogy Sep 26, 2018 •

edited

Loading

Uh oh!

xiaomaogy commented Sep 26, 2018

Uh oh!

Uh oh!

		@@ -0,0 +1,75 @@
		# Learning Brains

		The Learning Brain work in different phases of

Develop scriptable brains documentation #1249

Develop scriptable brains documentation #1249

Uh oh!

Conversation

vincentpierre commented Sep 21, 2018 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

vincentpierre Sep 25, 2018 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

awjuliani commented Sep 24, 2018

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

xiaomaogy Sep 26, 2018 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

xiaomaogy commented Sep 26, 2018

Uh oh!

Uh oh!

vincentpierre commented Sep 21, 2018 •

edited

Loading

vincentpierre Sep 25, 2018 •

edited

Loading

xiaomaogy Sep 26, 2018 •

edited

Loading