GridWorld now uses action masking #1125
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
mmattar
suggested changes
Aug 25, 2018
mmattar
left a comment
mmattar
left a comment
There was a problem hiding this comment.
Can you add the tensorboard comparison graphs?
| var positionX = (int) transform.position.x; | ||
| var positionZ = (int) transform.position.z; | ||
| var maxPosition = academy.gridSize - 1; | ||
| if (positionX == 0) |
There was a problem hiding this comment.
the constants 0 -> 3 in the conditionals (if position...) and in SetActionMask should be class static variables.
mmattar
suggested changes
Aug 27, 2018
| int action = Mathf.FloorToInt(vectorAction[0]); | ||
|
|
||
| // 0 - Forward, 1 - Backward, 2 - Left, 3 - Right | ||
| Vector3 targetPos = transform.position; |
| // Prevents the agent from picking an action that would make it collide with a wall | ||
| var positionX = (int) transform.position.x; | ||
| var positionZ = (int) transform.position.z; | ||
| var maxPosition = academy.gridSize - 1; |
There was a problem hiding this comment.
can the grid size be changed at runtime? If not, move this to InitializeAgent
Contributor
Author
There was a problem hiding this comment.
It can be changed at runtime yes. It is one of the reset maramiters.
* Added checkbox to turn action masking on/off * Fix to handle the no-action option
mmattar
approved these changes
Aug 29, 2018
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Outdated suggestions cannot be applied.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.
Action masking makes GridWorld learn faster because it does not waste time bumping into walls.
