Improvements to Learning-Environment-Create-New.md #3773
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Changed the ordered list to use "1." - Trimmed down text - Removed reference to materials as those are in the Example Envs project
chriselion
reviewed
Apr 16, 2020
|
|
||
| ### Initialization and Resetting the Agent | ||
|
|
||
| When the Agent reaches its target, its episode ends and the `OnEpisodeBegin()` | ||
| method moves the target to a random location. In addition, if the Agent rolls | ||
| When the Agent (Sphere) reaches its target (Cube), its episode ends and the `OnEpisodeBegin()` |
There was a problem hiding this comment.
This paragraph doesn't actually talk about "Initialization" even though it's in the section title. Maybe mention that Initialization is called at the start of simulation too?
chriselion
reviewed
Apr 16, 2020
| To solve the task of moving towards the target, the Agent (Sphere) needs to be able to | ||
| move in the `x` and `z` directions. As such, we will provide 2 actions to the agent. | ||
| The first determines the force applied along the x-axis; the second | ||
| determines the force applied along the z-axis. (If we allowed the Agent to move in three dimensions, then we would need a third action. |
chriselion
reviewed
Apr 16, 2020
chriselion
reviewed
Apr 16, 2020
| actionsOut[0] = Input.GetAxis("Horizontal"); | ||
| actionsOut[1] = Input.GetAxis("Vertical"); | ||
| } | ||
| public override float[] Heuristic() |
There was a problem hiding this comment.
Old code was correct, see #3765
chriselion
reviewed
Apr 16, 2020
| @@ -473,7 +420,7 @@ localPosition rather than position, so that our position reference is in referen | |||
| to the prefab TrainingArea's location, and not global coordinates. | |||
|
|
|||
| 1. Replace all references of `this.transform.position` in RollerAgent.cs with `this.transform.localPosition`. | |||
| 2. Replace all references of `Target.position` in RollerAgent.cs with `Target.localPosition`. | |||
| 1. Replace all references of `Target.position` in RollerAgent.cs with `Target.localPosition`. | |||
There was a problem hiding this comment.
Should we just start with these in the example, instead of changing them later? There's been some confusion before because the examples conflict with the best practices that we call out elsewhere.
chriselion
reviewed
Apr 17, 2020
| In many of the [example environments](Learning-Environment-Examples.md), many | ||
| copies of the training area are instantiated in the scene. This generally speeds | ||
| up training, allowing the environment to gather many experiences in parallel. | ||
| This can be achieved simply by instantiating many Agents which share the |
There was a problem hiding this comment.
which share the
Behavior Parameters
This isn't really accurate; they should have identical Behavior Parameters but they're not actually "shared" .
chriselion
approved these changes
Apr 17, 2020
added 2 commits
April 16, 2020 21:07
removed unnecessary configs updated the agent image
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Proposed change(s)
Describe the changes made in this PR.
Useful links (Github issues, JIRA tickets, ML-Agents forum threads etc.)
Types of change(s)
Checklist
Other comments